In this article, we introduce a compositional linguistic approach for attitude recognition in text. There are several aspects that distinguish our attitude analysis model (@AM) from other systems. First, our method classifies sentences using fine‐grained attitude labels (nine for affective states, two for positive and negative judgment, and two for positive and negative appreciation), as compared against other methods that mainly focus on two sentiment categories (positive and negative) or basic emotions. Next, our @AM is based on the analysis of syntactic and dependence relations between words in a sentence, the compositionality principle, a novel linguistic approach based on the rules elaborated for semantically distinct verb classes, and a method considering the hierarchy of concepts. As distinct from the state‐of‐the‐art approaches, the proposed method extensively deals with the semantics of terms, processes sentences of different complexity, handles not only correctly written text but also informal messages, and encodes the strength and the level of confidence of attitude through numerical values. The performance of our @AM was evaluated on data sets represented by sentences from different domains. @AM achieved a high level of accuracy on sentences from personal stories about life experiences, fairy tales, and news headlines, outperforming other methods on several measures.

This article describes a novel intelligent interface for attitude sensing in text driven by a robust computational tool for the analysis of fine-grained attitudes (emotions, judgments, and appreciations) expressed in text. The module responsible for textual attitude analysis was developed using a compositional linguistic approach based on the attitude-conveying lexicon, the analysis of syntactic and dependency relations between words in a sentence, the compositionality principle applied at various grammatical levels, the rules elaborated for semantically distinct verb classes, and a method considering the hierarchy of concepts. The performance of this module was evaluated on sentences from personal stories about life experiences. The developed web-based interface supports recognition of nine emotions, positive and negative judgments, and positive and negative appreciations conveyed in text. It allows users to adjust parameters, to enable or disable various functionality components of the algorithm, and to select the format of text annotation and attitude statistics visualization.

The World Wide Web includes semantic relations of numerous types that exist among different entities. Extracting the relations that exist between two entities is an important step in various Web-related tasks such as information retrieval (IR), information extraction, and social network extraction. A supervised relation extraction system that is trained to extract a particular relation type (source relation) might not accurately extract a new type of a relation (target relation) for which it has not been trained. However, it is costly to create training data manually for every new relation type that one might want to extract. We propose a method to adapt an existing relation extraction system to extract new relation types with minimum supervision. Our proposed method comprises two stages: learning a lower dimensional projection between different relations, and learning a relational classifier for the target relation type with instance sampling. First, to represent a semantic relation that exists between two entities, we extract lexical and syntactic patterns from contexts in which those two entities co-occur. Then, we construct a bipartite graph between relation-specific (RS) and relation-independent (RI) patterns. Spectral clustering is performed on the bipartite graph to compute a lower dimensional projection. Second, we train a classifier for the target relation type using a small number of labeled instances. To account for the lack of target relation training instances, we present a one-sided under sampling method. We evaluate the proposed method using a data set that contains 2,000 instances for 20 different relation types. Our experimental results show that the proposed method achieves a statistically significant macroaverage F-score of 62.77. Moreover, the proposed method outperforms numerous baselines and a previously proposed weakly supervised relation extraction method.

Predicting entailment between two given texts is an important task upon which the performance of numerous NLP tasks depend on such as question answering, text summarization, and information extraction. The degree to which two texts are similar has been used extensively as a key feature in much previous work in predicting entailment. However, using similarity scores directly, without proper transformations, results in suboptimal performance. Given a set of lexical similarity measures, we propose a method that jointly learns both (a) a set of non-linear transformation functions for those similarity measures and, (b) the optimal non-linear combination of those transformation functions to predict textual entailment. Our method consistently outperforms numerous baselines, reporting a micro-averaged F-score of 46.48 on the RTE- 7 benchmark dataset. The proposed method is ranked 2-nd among 33 entailment systems participated in RTE-7, demonstrating its competitiveness over numerous other entailment approaches. Although our method is statistically comparable to the current state-of-the-art, we require less external knowledge resources.

Personal name disambiguation is an important task in social network extraction, evaluation and integration of ontologies, information retrieval, cross‐document coreference resolution and word sense disambiguation. We propose an unsupervised method to automatically annotate people with ambiguous names on the Web using automatically extracted keywords. Given an ambiguous personal name, first, we download text snippets for the given name from a Web search engine. We then represent each instance of the ambiguous name by a term‐entity model (TEM), a model that we propose to represent the Web appearance of an individual. A TEM of a person captures named entities and attribute values that are useful to disambiguate that person from his or her namesakes (i.e., different people who share the same name). We then use group average agglomerative clustering to identify the instances of an ambiguous name that belong to the same person. Ideally, each cluster must represent a different namesake. However, in practice it is not possible to know the number of namesakes for a given ambiguous personal name in advance. To circumvent this problem, we propose a novel normalized cuts‐based cluster stopping criterion to determine the different people on the Web for a given ambiguous name. Finally, we annotate each person with an ambiguous name using keywords selected from the clusters. We evaluate the proposed method on a data set of over 2500 documents covering 200 different people for 20 ambiguous names. Experimental results show that the proposed method outperforms numerous baselines and previously proposed name disambiguation methods. Moreover, the extracted keywords reduce ambiguity of a name in an information retrieval task, which underscores the usefulness of the proposed method in real‐world scenarios.

Latent relational search is a novel entity retrieval paradigm based on the proportional analogy between two entity pairs. Given a latent relational search query {(Japan, Tokyo), (France, ?)}, a latent relational search engine is expected to retrieve and rank the entity “Paris” as the first answer in the result list. A latent relational search engine extracts entities and relations between those entities from a corpus, such as the Web. Moreover, from some supporting sentences in the corpus, (e.g., “Tokyo is the capital of Japan” and “Paris is the capital and biggest city of France”), the search engine must recognize the relational similarity between the two entity pairs. In cross-language latent relational search, the entity pairs as well as the supporting sentences of the first entity pair and of the second entity pair are in different languages. Therefore, the search engine must recognize similar semantic relations across languages. In this article, we study the problem of cross-language latent relational search between Japanese and English using Web data. To perform cross-language latent relational search in high speed, we propose a multi-lingual indexing method for storing entities and lexical patterns that represent the semantic relations extracted from Web corpora. We then propose a hybrid lexical pattern clustering algorithm to capture the semantic similarity between lexical patterns across languages. Using this algorithm, we can precisely measure the relational similarity between entity pairs across languages, thereby achieving high precision in the task of cross-language latent relational search. Experiments show that the proposed method achieves an MRR of 0.605 on Japanese-English cross-language latent relational search query sets and it also achieves a reasonable performance on the INEX Entity Ranking task.

Latent relational search (LRS) is a novel approach for mapping knowledge across two domains. Given a source domain knowledge concerning the Moon, "The Moon is a satellite of the Earth," one can form a question {(Moon, Earth), (Ganymede, ?)} to query an LRS engine for new knowledge in the target domain concerning the Ganymede. An LRS engine relies on some supporting sentences such as ``Ganymede is a natural satellite of Jupiter.'' to retrieve and rank "Jupiter" as the first answer. This paper proposes cross-language latent relational search (CLRS) to extend the knowledge mapping capability of LRS from cross-domain knowledge mapping to cross-domain and cross-language knowledge mapping. In CLRS, the supporting sentences for the source pair might be in a different language with that of the target pair. We represent the relation between two entities in an entity pair by lexical patterns of the context surrounding the two entities. We then propose a novel hybrid lexical pattern clustering algorithm to capture the semantic similarity between paraphrased lexical patterns across languages. Experiments on Japanese-English datasets show that the proposed method achieves an MRR of 0.579 for CLRS task, which is comparable to the MRR of an existing monolingual LRS engine.

Real-world social networks are dynamic in nature. Companies continue to collaborate, align strategically, acquire, and merge over time, and receive positive/negative impact from other companies. Consequently, their performance changes with time. If one can understand what types of network changes affect a company's value, he/she can predict the future value of the company, grasp industry innovations, and make business more successful. However, it often requires continuous records of relational changes, which are often difficult to track for companies, and the models of mining longitudinal network are quite complicated. In this study, we developed algorithms and a system to infer large-scale evolutionary company networks from public news during 1981-2009. Then, based on how networks change over time, as well as the financial information of the companies, we predicted company profit growth. This is the first study of longitudinal network-mining-based company performance analysis in the literature

Abstract In this paper, we address the tasks of recognition and interpretation of affect communicated through text messaging in online communication environments. Specifically, we focus on Instant Messaging (IM) or blogs, where people use an informal or garbled style of writing. We introduced a novel rule-based linguistic approach for affect recognition from text. Our Affect Analysis Model (AAM) was designed to deal with not only grammatically and syntactically correct textual input, but also informal messages written in an abbreviated or expressive manner. The proposed rule-based approach processes each sentence in stages, including symbolic cue processing, detection and transformation of abbreviations, sentence parsing and word/phrase/sentence-level analyses. Our method is capable of processing sentences of different complexity, including simple, compound, complex (with complement and relative clauses) and complex–compound sentences. Affect in text is classified into nine emotion categories (or neutral). The strength of the resulting emotional state depends on vectors of emotional words, relations among them, tense of the analysed sentence and availability of first person pronouns. The evaluation of the Affect Analysis Model algorithm showed promising results regarding its capability to accurately recognize fine-grained emotions reflected in sentences from diary-like blog posts (averaged accuracy is up to 77 per cent), fairy tales (averaged accuracy is up to 70.2 per cent) and news headlines (our algorithm outperformed eight other systems on several measures).

In this paper, we describe methods to automatically generate and score a new sentiment lexicon, called SentiFul, and expand it through direct synonymy and antonymy relations, hyponymy relations, derivation, and compounding with known lexical units. We propose to distinguish four types of affixes (used to derive new words) depending on the role they play with regard to sentiment features: propagating, reversing, intensifying, and weakening. Besides derivation, we considered important process of finding new words such as compounding, which is a highly productive process, especially in the case of nouns and adjectives. We elaborated the algorithm for automatic extraction of new sentiment-related compounds from WordNet using words from SentiFul as seeds for sentiment-carrying base components and applying the patterns of compound formations. In the paper, the importance of considering modifiers, contextual valence shifters, and modal operators, which are integral parts of the SentiFul lexicon for robust sentiment analysis, is also discussed.

An individual is typically referred by numerous name aliases on the web. Accurate identification of aliases of a given person name is useful in various web related tasks such as information retrieval, sentiment analysis, personal name disambiguation, and relation extraction. We propose a method to extract aliases of a given personal name from the web. Given a personal name, the proposed method first extracts a set of candidate aliases. Second, we rank the extracted candidates according to the likelihood of a candidate being a correct alias of the given name. We propose a novel, automatically extracted lexical pattern-based approach to efficiently extract a large set of candidate aliases from snippets retrieved from a web search engine. We define numerous ranking scores to evaluate candidate aliases using three approaches: lexical pattern frequency, word co-occurrences in an anchor text graph, and page counts on the web. To construct a robust alias detection system, we integrate the different ranking scores into a single ranking function using ranking support vector machines. We evaluate the proposed method on three data sets: an English personal names data set, an English place names data set, and a Japanese personal names data set. The proposed method outperforms numerous baselines and previously proposed name alias extraction methods, achieving a statistically significant mean reciprocal rank (MRR) of 0.67. Experiments carried out using location names and Japanese personal names suggest the possibility of extending the proposed method to extract aliases for different types of named entities, and for different languages. Moreover, the aliases extracted using the proposed method are successfully utilized in an information retrieval task and improve recall by 20 percent in a relation-detection task.

Measuring the semantic similarity between words is an important component in various tasks on the web such as relation extraction, community mining, document clustering, and automatic metadata extraction. Despite the usefulness of semantic similarity measures in these applications, accurately measuring semantic similarity between two words (or entities) remains a challenging task. We propose an empirical method to estimate semantic similarity using page counts and text snippets retrieved from a web search engine for two words. Specifically, we define various word co-occurrence measures using page counts and integrate those with lexical patterns extracted from text snippets. To identify the numerous semantic relations that exist between two given words, we propose a novel pattern extraction algorithm and a pattern clustering algorithm. The optimal combination of page counts-based co-occurrence measures and lexical pattern clusters is learned using support vector machines. The proposed method outperforms various baselines and previously proposed web-based semantic similarity measures on three benchmark data sets showing a high correlation with human ratings. Moreover, the proposed method significantly improves the accuracy in a community mining task.

The aim of this paper is two-fold. First, it describes a scripting language for specifying communicative behavior and interaction of computer-controlled agents ("bots") in the popular three-dimensional (3D) multiuser online world of "Second Life" and the emerging "OpenSimulator" project. While tools for designing avatars and in-world objects in Second Life exist, technology for nonprogrammer content creators of scenarios involving scripted agents is currently missing. Therefore, we have implemented new client software that controls bots based on the Multimodal Presentation Markup Language 3D (MPML3D), a highly expressive XML-based scripting language for controlling the verbal and nonverbal behavior of interacting animated agents. Second, the paper compares Second Life and OpenSimulator platforms and discusses the merits and limitations of each from the perspective of agent control. Here, we also conducted a small study that compares the network performance of both platforms.

Binary semantic relation extraction is particularly useful for various NLP and Web applications. Currently Web-based methods and Linguistic-based methods are two types of leading methods for semantic relation extraction task. With a novel view on integrating linguistic analysis on local text with Web frequent information, we propose a multi-view co-clustering approach for semantic relation extraction. One is feature clustering by automatically learning clustering functions for Web features, linguistic features simultaneously based on a subset of entity pairs. The other is relation clustering, using the feature clustering functions to define learning function for relation extraction. Our experiments demonstrate the superiority of our clustering approach comparing with several state-of-the-art clustering methods.

Latent relational search is a new search paradigm based on the degree of analogy between two word pairs. A latent relational search engine is expected to return the word Paris as an answer to the question mark (?) in the query {(Japan, Tokyo), (France, ?)} because the relation between Japan and Tokyo is highly similar to that between France and Paris. We propose an approach for exploring and indexing word pairs to efficiently retrieve candidate answers for a latent relational search query. Representing relations between two words in a word pair by lexical patterns allows our search engine to achieve a high MRR and high precision for the top 1 ranked result. When evaluating with a Web corpus, the proposed method achieves an MRR of 0.963 and it retrieves correct answer in the top 1 for 95.0% of queries.

In this paper, we propose a Relation Expansion framework, which uses a few seed sentences marked up with two entities to expand a set of sentences containing target relations. During the expansion process, label propagation algorithm is used to select the most confident entity pairs and context patterns. The label propagation algorithm is a graph based semi-supervised learning method which models the entire data set as a weighted graph and the label score is propagated on this graph. We test the proposed framework with four relationships, the results show that the label propagation is quite competitive comparing with existing methods.

Extracting semantic relations among entities is an important first step in various tasks in Web mining and natural language processing such as information extraction, relation detection, and social network mining. A relation can be expressed extensionally by stating all the instances of that relation or intensionally by defining all the paraphrases of that relation. For example, consider the ACQUISITION relation between two companies. An extensional definition of ACQUISITION contains all pairs of companies in which one company is acquired by another (e.g. (YouTube, Google) or (Powerset, Microsoft)). On the other hand we can intensionally define ACQUISITION as the relation described by lexical patterns such as X is acquired by Y, or Y purchased X, where X and Y denote two companies. We use this dual representation of semantic relations to propose a novel sequential co-clustering algorithm that can extract numerous relations efficiently from unlabeled data. We provide an efficient heuristic to find the parameters of the proposed coclustering algorithm. Using the clusters produced by the algorithm, we train an L1 regularized logistic regression model to identify the representative patterns that describe the relation expressed by each cluster. We evaluate the proposed method in three different tasks: measuring relational similarity between entity pairs, open information extraction (Open IE), and classifying relations in a social network system. Experiments conducted using a benchmark dataset show that the proposed method improves existing relational similarity measures. Moreover, the proposed method significantly outperforms the current state-of-the-art Open IE systems in terms of both precision and recall. The proposed method correctly classifies 53 relation types in an online social network containing 470; 671 nodes and 35; 652; 475 edges, thereby demonstrating its efficacy in real-world relation detection tasks.

News is an interesting application domain for “emotion sensing”, since readers often have a personal attitude or subjective opinion regarding certain events or entities reported about. Hence the ability to determine user-centric emotion on a given to

Many efforts are undertaken by people and companies to improve their popularity, growth, and power, the outcomes of which are all expressed as rankings (designated as target rankings). Are these rankings merely the results of its elements' own attributes? In the theory of social network analysis (SNA), the performance and power of actors are usually interpreted as relations and the relational structures they embedded. In this study, we propose an algorithm to generate and integrate network-based features systematically from a given social network that mined from the Web to learn a model for explaining target rankings. Experimental results for learning to rank researchers' productivity based on social networks confirm the effectiveness of our models. This paper specifically examines the application of a social network that provides an example of advanced utilization of social networks mined from the Web.

In this paper, the authors extend previous work on the automatic structuring of medical documents using content analysis. Their long-term objective is to take advantage of specific rhetoric markers encountered in specialized medical documents (clinical guidelines) to automatically structure free text according to its role in the document. This should enable to generate multiple views of the same document depending on the target audience, generate document summaries, as well as facilitating knowledge extraction from text. The authors have established in previous work that the structure of clinical guidelines could be refined through the identification of a limited set of deontic operators. They now propose to extend this approach by analyzing the text delimited by these operators using Rhetorical Structure Theory. The emphasis on causality and time in RST proves a powerful complement to the recognition of deontic structures while retaining the same philosophy of high-level recognition of sentence structure, which can be converted into applicationspecific mark-ups. Throughout the paper, the authors illustrate their findings through results produced by the automatic processing of English guidelines for the management of hypertension and Alzheimer disease.

Measuring the similarity between implicit semantic relations is an important task in information retrieval and natural language processing. For example, consider the situation where you know an entity-pair (e.g. Google, YouTube), between which a particular relation holds (e.g. acquisition), and you are interested in retrieving other entity-pairs for which the same relation holds (e.g. Yahoo, Inktomi). Existing keyword-based search engines cannot be directly applied in this case because in keyword-based search, the goal is to retrieve documents that are relevant to the words used in the query -- not necessarily to the relations implied by a pair of words. Accurate measurement of relational similarity is an important step in numerous natural language processing tasks such as identification of word analogies, and classification of noun-modifier pairs. We propose a method that uses Web search engines to efficiently compute the relational similarity between two pairs of words. Our method consists of three components: representing the various semantic relations that exist between a pair of words using automatically extracted lexical patterns, clustering the extracted lexical patterns to identify the different semantic relations implied by them, and measuring the similarity between different semantic relations using an inter-cluster correlation matrix. We propose a pattern extraction algorithm to extract a large number of lexical patterns that express numerous semantic relations. We then present an efficient clustering algorithm to cluster the extracted lexical patterns. Finally, we measure the relational similarity between word-pairs using inter-cluster correlation. We evaluate the proposed method in a relation classification task. Experimental results on a dataset covering multiple relation types show a statistically significant improvement over the current state-of-the-art relational similarity measures.

Measuring the similarity between semantic relations that hold among entities is an important and necessary step in various Web related tasks such as relation extraction, information retrieval and analogy detection. For example, consider the case in which a person knows a pair of entities (e.g. Google, YouTube), between which a particular relation holds (e.g. acquisition). The person is interested in retrieving other such pairs with similar relations (e.g. Microsoft, Powerset). Existing keyword-based search engines cannot be applied directly in this case because, in keyword-based search, the goal is to retrieve documents that are relevant to the words used in a query -- not necessarily to the relations implied by a pair of words. We propose a relational similarity measure, using a Web search engine, to compute the similarity between semantic relations implied by two pairs of words. Our method has three components: representing the various semantic relations that exist between a pair of words using automatically extracted lexical patterns, clustering the extracted lexical patterns to identify the different patterns that express a particular semantic relation, and measuring the similarity between semantic relations using a metric learning approach. We evaluate the proposed method in two tasks: classifying semantic relations between named entities, and solving word-analogy questions. The proposed method outperforms all baselines in a relation classification task with a statistically significant average precision score of 0.74. Moreover, it reduces the time taken by Latent Relational Analysis to process 374 word-analogy questions from 9 days to less than 6 hours, with an SAT score of 51%.

Measuring relational similarity between words is important in numerous natural language processing tasks such as solving analogy questions and classifying noun-modifier relations. We propose a method to measure the similarity between semantic relations that hold between two pairs of words using a web search engine. First, each pair of words is represented by a vector of automatically extracted lexical patterns. Then a Support Vector Machine is trained to recognize word pairs with similar semantic relations. We evaluate the proposed method on SAT multiple-choice word-analogy questions. The proposed method achieves a score of 40% which is comparable with relational similarity measures which use manually created resources such as WordNet. The proposed method significantly reduces the time taken by previously proposed computationally intensive methods, such as latent relational analysis, to process 374 analogy questions from 8 days to less than 6 hours.

Confronting the challenges of annotating naturally occurring text into a semantically structured form to facilitate automatic information extraction, current semantic role labeling (SRL) systems have been specifically examining a semantic predicate-argument structure. Based on the concept description language for natural language (CDL.nl) which is intended to describe the concept structure of text using a set of pre-defined semantic relations, we develop a parser to add a new layer of semantic annotation of natural language sentences as an extension of SRL. With the assumption that all relation instances are detected, we present a relation classification approach facing the challenges of CDL.nl relation extraction. Preliminary evaluation on a manual dataset, using support vector machine, shows that CDL.nl relations can be classified with good performance.

We propose a novel approach to find aliases of a given name from the web. We exploit a set of known names and their aliases as training data and extract lexical patterns that convey information related to aliases of names from text snippets returned by a web search engine. The patterns are then used to find candidate aliases of a given name. We use anchor texts and hyperlinks to design a word co-occurrence model and define numerous ranking scores to evaluate the association between a name and its candidate aliases. The proposed method outperforms numerous baselines and previous work on alias extraction on a dataset of personal names, achieving a statistically significant mean reciprocal rank of 0.6718. Moreover, the aliases extracted using the proposed method improve recall by 20% in a relation-detection task.

In this paper, we describe an interface consisting of a virtual showroom where a team of two highly realistic 3D agents presents product items in an entertaining and attractive way. The presentation flow adapts to users' attentiveness, or lack thereof, and may thus provide a more personalized and user-attractive experience of the presentation. In order to infer users' attention and visual interest regarding interface objects, our system analyzes eye movements in real-time. Interest detection algorithms used in previous research determine an object of interest based on the time that eye gaze dwells on that object. However, this kind of algorithm is not well suited for dynamic presentations where the goal is to assess the user's focus of attention regarding a dynamically changing presentation. Here, the current context of the object of attention has to be considered, i.e., whether the visual object is part of (or contributes to) the current presentation content or not. Therefore, we propose a new approach that estimates the interest (or non-interest) of a user by means of dynamic Bayesian networks. Each of a predefined set of visual objects has a dynamic Bayesian network assigned to it, which calculates the current interest of the user in this object. The estimation takes into account (1) each new gaze point, (2) the current context of the object, and (3) preceding estimations of the object itself. Based on these estimations the presentation agents can provide timely and appropriate response.

In this paper we introduce a system that automatically adds different types of non-verbal behavior to a given dialogue script between two virtual embodied agents. It allows us to transform a dialogue in text format into an agent behavior script enriched by eye gaze and conversational gesture behavior. The agents' gaze behavior is informed by theories of human face-to-face gaze behavior. Gestures are generated based on the analysis of linguistic and contextual information of the input text. The resulting annotated dialogue script is then transformed into the Multimodal Presentation Markup Language for 3D agents (MPML3D), which controls the multi-modal behavior of animated life-like agents, including facial and body animation and synthetic speech. Using our system makes it very easy to add appropriate non-verbal behavior to a given dialogue text, a task that would otherwise be very cumbersome and time consuming.

In this paper, we focus on affect recognition from text in order to facilitate sensitive and expressive communication in computer-mediated environments. Our model for analyzing affect conveyed by text is tailored to handle the style and specifics of informal online conversations. The motivation behind our approach is to improve social interactivity and emotional expressiveness of real-time messaging.In order to estimate affect in text, our model processes symbolic cues, such as emoticons, detects and transforms abbreviations, and employs natural language processing techniques for word/phrase/sentence-level analysis, e.g. by considering relations among words in a sentence. As a result of the analysis, text can be categorized into emotional states and communicative functions. A designed graphical representation of a user (avatar) displays emotions and social behaviour driven by text and performs natural idle movements. The proposed system shows promising results on affect recognition in real examples of online conversation.

This paper presents a multi-modal presentation markup language for humanoid robots, MPML-HR ver. 3.0, which is able to describe presentation contents including speech-based interactions with audiences. Previous versions of MPML-HR do not feature any interaction functionality which dynamically changes the presentation according to the utterances by audiences, although such interaction makes the presentation more effective and understandable. Since MPML-HR ver. 3.0 inherits simple descriptions of previous versions of MPML-HR, the content designer can describe interactive presentations without configuring conventional complicated multi-modal interactive systems.

This paper describes a character-based system called "Emotion Sensitive News Agent" (ESNA). ESNA is been developed as a news aggregator to fetch news from different news sources chosen by a user, and to categorize the themes of the news into eight emotion types. A small user study indicates that the system is conceived as intelligent and interesting as an affective interface. ESNA exemplifies a recent research agenda that aims at recognizing affective information conveyed through texts. News is an interesting application domain where user may have marked attitudes to certain events or entities reported about. Different approaches have already been employed to "sense" emotion from text. The novelty of our approach is twofold: affective information conveyed through text is analyzed (1) by considering the cognitive and appraisal structure of emotions, and (2) by taking into account user preferences.

Collaborative tagging is increasingly drawing attentions. However the keyword based tagging scheme has its limitations and it can be observed that tagging society are seeking and using new tagging patterns. This paper proposes a subject-predicate-object scheme for users to triple tag web resources. We first introduce the triple tag model and discuss its relations with existing tag schema and RDF model. Then a filter-based framework that supports the query of triple tags is proposed. The implementation and a case study in the comparison shopping domain are exhibited.

Article Share on Measuring semantic similarity between words using web search enginesWWW '07: Proceedings of the 16th international conference on World Wide WebMay 2007 Pages 757–766https://doi.org/10.1145/1242572.1242675Online:08 May 2007Publication History 123citation3,949DownloadsMetricsTotal Citations123Total Downloads3,949Last 12 Months94Last 6 weeks13 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

We motivate an approach to evaluating the utility of life-like interface agents that is based on human eye movements rather than questionnaires. An eye tracker is employed to obtain quantitative evidence of a user’s focus of attention without distracting from the primary task. The salient feature of our evaluation strategy is that it allows us to measure important properties of a user’s interaction experience on a moment-by-moment basis in addition to a cumulative (spatial) analysis of the user’s areas of interest. We describe a pilot study in which we compare attending behavior of subjects watching the presentation of a computer-generated apartment layout and visualization augmented by three types of media: an animated agent, a text box, and speech only. The investigation of eye movements revealed that deictic gestures performed by the agent are more effective in directing the attentional focus of subjects to relevant interface objects than the media used in the two control conditions, at a slight cost of distracting the user from visual inspection of the object of reference. The results also demonstrate that the presence of an interface agent seemingly triggers natural and social interaction protocols of human users.

Ordering information is a difficult but important task for applications generating natural-language text. We present a bottom-up approach to arranging sentences extracted for multi-document summarization. To capture the association and order of two textual segments (eg, sentences), we define four criteria, chronology, topical-closeness, precedence, and succession. These criteria are integrated into a criterion by a supervised learning approach. We repeatedly concatenate two textual segments into one segment based on the criterion until we obtain the overall segment with all sentences arranged. Our experimental results show a significant improvement over existing sentence ordering strategies.

This paper describes an empathic software agent (ESA) interface using eye movement information to facilitate empathy-relevant reasoning and behavior. Eye movement tracking is used to monitor user's attention and interests, and to personalize the agent behaviors. The system reacts to user eye information in real-time, recording eye gaze and pupil dilation data during the learning process. Based on these measures, the ESA infers the focus of attention and motivational status of the learner and responds accordingly with affective (display of emotion) and instructional behaviors. In addition to describing the design and implementation of empathic software agents, this paper will report on some preliminary usability test results concerning how users respond to the empathic functions that are provided.

Both on-screen agents and humanoid robots are increasingly used as human-computer interfaces. This study evaluates an on-screen agent and a humanoid robot in the task of one-sided presentations. We compared the participant's subjective impressions of nearly identical presentation contents performed by each presenter. The results derived by the semantic differential (SD) method and the direct questioning show that each presenter has different functional advantages. We infer that on-screen agent and robot can complement each other in presentations

Studying the relationship between natural language and affective information as well as assessing the underpinned affective qualities of natural language are becoming crucial for improving human computer interaction. Different approaches have already been employed to "sense" affective information from text but none of those considered the cognitive structure of individual emotions and appraisal structure of those emotions adopted by emotion sensing programs. It has also been observed that previous attempts for textual affect sensing have categorized texts into a number of emotion groups, e.g. six so-called "basic" emotion proposed by Paul Ekman which we believe insufficient to classify textual emotions. Hence we propose a different approach to sense affective information from texts by applying the cognitive theory of emotions known as OCC model [1] which distinguishes several emotion types that can be identified by assessing valenced reactions to events, agents or objects described in the texts. In particular we want to create a formal model that can not only "understand" what emotions people wrap with their textual messages, but also can make automatic empathic response with respect to the emotional state detected in the text (e.g. in a chat system). We first briefly describe relevant works and then we explain our proposal with examples. Finally we conclude with future work plans.

Recent interest in the use of software character agents raises the issue of how many agents should be used in online learning. In this paper we review evidence concerning the relative effectiveness of multi-agent systems and introduce a multiple agent system that we have developed for online instruction. A user test is carried out that compares one and two agent versions of the learning system. The results are interpreted in terms of their implications for selecting when and how more than one agent should be used in online learning. We conclude with some recommendations on when multiple agents may help online learners to interact with the learning environment more easily and efficiently.

Due to availability and accessibility of enormous Internet-based resources and dynamic nature of Web pages, the task of information retrieval is becoming more challenging and gradually tricky. This paper describes about agent based autonomous system, automatic report to presentation (ARP), with the notion of autonomous information service emerging as the result of integration among natural language processing, Web intelligence, and character-based agent interaction. The system, ARP, automatically builds a report on a topic or search phrase(s) given by a user by fetching a set of Web-pages; and then parsing; summarizing, affect-sensing and correlating information extracted from those. The system also makes a concise presentation automatically and, a group of character based software-agents autonomously present the topic in a story-telling manner employing text- to-speech engine with accompanied content-rich slides, different gestures and affects

Social networks play important roles in the Semantic Web: knowledge management, information retrieval, ubiquitous computing, and so on. We propose a social network extraction system called POLYPHONET, which employs several advanced techniques to extract relations of persons, detect groups of persons, and obtain keywords for a person. Search engines, especially Google, are used to measure co-occurrence of information and obtain Web documents.Several studies have used search engines to extract social networks from the Web, but our research advances the following points: First, we reduce the related methods into simple pseudocodes using Google so that we can build up integrated systems. Second, we develop several new algorithms for social networking mining such as those to classify relations into categories, to make extraction scalable, and to obtain and utilize person-to-word relations. Third, every module is implemented in POLYPHONET, which has been used at four academic conferences, each with more than 500 participants. We overview that system. Finally, a novel architecture called Super Social Network Mining is proposed; it utilizes simple modules using Google and is characterized by scalability and Relate-Identify processes: Identification of each entity and extraction of relations are repeated to obtain a more precise social network.

We motivate an approach to evaluating the utility of life-like interface agents that is based on human eye movements rather than questionnaires. An eye tracker is employed to obtain quantitative evidence of a user's focus of attention. The salient feature of our evaluation strategy is that it allows us to measure important properties of a user's interaction experience on a moment-by-moment basis in addition to a cumulative (spatial) analysis of the user's areas of interest. We describe an empirical study in which we compare attending behavior of subjects watching the presentation of an apartment by three types of media: an animated agent, a text box, and speech only. The investigation of users' eye movements reveals that agent behavior may trigger natural and social interaction behavior of human users.

It is necessary to determine a proper arrangement of extracted sentences to generate a well-organized summary from multiple documents. This paper describes our Multi-Document Summarization (MDS) system for TSC-3. It specifically addresses an approach to coherent sentence ordering for MDS. An impediment to the use of chronological ordering, which is widely used by conventional summarization system, is that it arranges sentences without considering the presupposed information of each sentence. We propose a method to improve chronological ordering by resolving precedent information of arranging sentences. Combining the refinement algorithm with topical segmentation and chronological ordering, we address our experiments and metrics to test the effectiveness of MDS tasks. Results demonstrate that the proposed method significantly improves chronological sentence ordering. At the end of the paper, we also report an outline/evaluation of important sentence extraction and redundant clause elimination integrated in our MDS system.

Research carried out in authoring systems for embodied agent based presentations have traditionally been confined to scripted interactive presentations. In recent years, however, there has been a gradual shift to adopting a more dynamic approach that supports a higher degree of flexibility in user-agent interactivity, where the user is allowed to engage in more natural conversations with the agent. In this paper, we will describe a conversational module based on techniques used in chat-bots, that we have implemented as an extension to our previously developed agent authoring system

In a ubiquitous computing environment, it is desirable to provide a user with information depending on a user's situation, such as time, location, user behavior, and social context. At conventions, such as academic conferences and exhibitions, where participants must register in advance, the social context of participants can be extracted from the Web using their names and affiliations without asking the participants many questions. Here, we attempt to extract the social network of participants from the Web, where a node represents a participant and an edge represents the relationship of two participants. Each edge is added using the number of pages retrieved by a search engine which include both participants names. Moreover, each edge has a label such as "coauthors" and "members of the same project" by applying classification rules to the page content. We show an example of the extracted network and make a preliminary evaluation. This network can be used in many information services, such as finding an appropriate introducer or negotiator, and who one should talk to in order to efficiently expand his/her network.

We develop a browsing support system which learns user's interests and highlights keywords based on a user's browsing history. Monitoring the user's access to the Web enable us to detect "familiar words" for the user. We extract keywords, which are relevant to the familiar words in the current page, and highlight them. The relevancy is measured by the biases of co-occurrence, called IRM (Interest Relevance Measure). Our system consists of three components; a proxy server which monitors access to the Web, a frequency server which stores frequency of words in the accessed Web pages, and a keyword extraction module. Preliminary reports are shown to evaluate the system.

Busy and no time to digest the news archive....? Ever since the Web wide-spreading, the amount of electronically available information online, especially news archive proliferates and threatens to overwhelm human attention. Seeing this, we propose an information system that will extract the main topics in the news archive in a weekly basis. By getting a weekly report, user can know what were the main news events in the past week. 1.

Rapid growth of competition on the electronic market place calls for innovative communication modes with web users. Considering the emergence of dynamic media objects containing temporal infromation such as animated character agents, web page scripts nowadays cannot satisfy users' increasing requirements well. We will develop a Dynamic Web Markup Language (DWML) as a software platform for authoring animated web pages with character agents. We assume that both primary media objects (text, image, etc.) and animated characters can be dynamic objects carrying time-based information, and that a character agent is a special dynamic medium as part of a multimedia interface. DWML, having a distributed structure and timeline flow, is used to generate both dynamic and static media objects, as well as characters' verbal and non-verbal behaviors.

The paper proposes a visual authoring tool for a presentation agent system on the Web. In presentation systems, it is more fascinating when we conduct the presentation stream via the explanation or conversation of presenters. In order to provide a presentation on demand on the Web, we need a character based presentation agent. There are several ways to control such agents but some are too complex to be used by general users; we propose an easy method for controlling agents. For this purpose, we have developed Multimodal Presentation Markup Language (MPML), which allows many users to write attractive multimodal presentations easily. MPML is a markup language conforming to Extensible Markup Language (XML) and it supports functions for controlling verbal presentation and agent behavior. The authors present MPML's specification, visual authoring tool, and the application of MPML when used as a tool for composing multimodal presentations on the WWW.

This paper promotes socially intelligent animated agents for the pedagogical task of English conversation training for native speakers of Japanese. As a novel feature, social role awareness is introduced to animated conversational agents, that are by non-strong affective reasoners, but otherwise often lack the social competence observed in humans. In particular, humans may easily adjust their behavior depending on their respective role in a social setting, whereas their synthetic pendants tend to be driven mostly by emotions and personality. Our main contribution is the incorporation of a "social filter program" to mental models of animated agents. This program may qualify an agent's expression of its emotional state by the social contest, thereby enhancing the agent's believability as a conversational partner. Our implemented system is web-based and demonstrates socially aware animated agents in a virtual coffee shop environment. An experiment with our conversation system shows that users consider socially aware agents as more natural than agents that violate conventional practices.

The phenomenon that a 'little' topic can make a big difference is called 'The Tipping Point'. As a strategy for marketing this phenomenon could be a great economic opportunity. For instance, at is a good strategy to promote items associated with a certain fashion. The Tipping Point refers to a situation where the topic matches potential needs of customers. We analyze the mechanism of The Tipping Point in the context of the WWW, and present an algorithm called 'Expected Activation' for discovering promising new topics on the WWW.

We present an approach to knowledge compilation that transforms a function-free first-order Horn knowledge base to propositional logic. This form of compilation is important since the most efficient reasoning methods are defined for propositional logic, while knowledge is most conveniently expressed within a first-order language. To obtain compact propositional representations, we employ techniques from (ir)relevance reasoning as well as theory transformation via unfold/fold transformations. Application areas include diagnosis, planning, and vision. Preliminary experiments with a hypothetical reasoner indicate that our method may yield significant speed-ups.

This paper describes briefly an algorithm both for real-time facial image recognition in unconstrained indoor environments and a human like agent image synthesis which responds to the recognition results. Our simple but effective image recognition algorithm can recognize facial images from moving images, choose one primal face and track the primal face in real-time. Therefore, the agent can gaze/glance/etc., at the primal face (the interacting user) during the process. It means a "facial contact" or an "eye contact" can be achieved between the user and the synthesized moving agent, which is very important for friendly human interfaces.

One crucial problem with a hypothetical reasoning system is its slow inference speed, while it is a very useful framework in knowledge processing. The authors present a fast mechanism for the hypothetical reasoning, by using analogy of results which were previously proved to be true. An inference-path network can be effectively used for selecting useful hypotheses from an analogous case, and for generating new additional hypotheses which are necessary for proving a new goal. The inference speed of the hypothetical reasoning, whose computational complexity has been proved to be NP-complete or NP-hard, cannot be improved from the exponential-order limit as long as we use ordinary search methods. It is shown that this limit can be overcome in average inference time by using analogy.

A hypothetical reasoning is an important knowledge system's framework because of its theoretical basis and its usefulness for practical problems including diagnosis, design, etc. One crucial problem with hypothetical reasoning is, however, its slow inference speed. The polynomial-time approximate solution method of equivalent 0-1 integer programming, i.e., pivot and complement method, has been applied to computing hypothetical reasoning. However, to achieve further improvement by considering the knowledge structure of a given problem, it is beneficial to have another inference method which can work in the knowledge domain rather than the mathematical programming domain. For this purpose, the above method is reformalized using a new type of network. By taking advantage of the knowledge structure, this network achieves an inference speed in the order of O(N/sup 2/) against N, where N indicates problem size.

GeneView is a newly developed human gene mapping library system that works on an X-Window platform. This system is designed for researchers who routinely utilize gene mapping data in the laboratory but are unfamiliar with computer technology. GeneView offers various features, including friendly user interface, fast operation and visualization facility. Genetic loci are displayed graphically with an idiogram. This system can be operated in multiple languages. A current version supports Japanese and English, and can be easily expanded to include other languages. A prototype of GeneView is now installed on a SPARC (Sun4) workstation. Because of the X-Window platform, GeneView should be compatible with various types of workstations.

Describes a parallel computing system and a software algorithm for realtime interaction between a human user and a synthesized moving humanlike image or agent. The realistic human-like agent appearing on a display can recognize the palm position and finger motion (finger sign) of the human user, then tracks and gazes at the hand position and changes his/her facial expression in response to the recognized finger sign in realtime. This kind of interactive agent is expected to play an important role in advanced human interfaces. To realize realtime image recognition and image synthesis, a parallel image processing and synthesis system named 'TN-VIT' has been developed.>

A fast hypothetical reasoning system is described which is named KICK-SHOTGAN, and which avoids inefficient backtracking by the forward synthesis of necessary hypothesis combination along this network. The formation of inference-path network is based on a linear-time algorithm for the satisfiability testing of propositional Horn clauses. This system differs from ATMS mainly in its total problem solving nature. That is, it works for the logical problem-solving framework which yields a solution for a given goal, whereas the ATMS calculates possible data supported by hypotheses incrementally in response to the input of a justification (rule) from a problem solver existing outside the ATMS.>

The methods of fast hypothetical reasoning systems developed for propositional logic cannot be applicable in a straightforward manner to the predicate-logic case. A fast hypothetical reasoning mechanism that is effective for predicate-logic knowledge (actually for function-free predicate Horn-clause knowledge) is presented. A reasoning method developed in the deductive database area is effectively applied to this mechanism.>

A 3-D vision system incorporating a solid modeler and a geometric reasoning mechanism is described. A mathematical method based on the perspective geometry is employed to determine the position of predefined shapes in 3-D space from a single-view image. The solid modeler allows the precise and reliable understanding of possible objects. Furthermore, it can be used to synthesize virtual images based on the understanding result. The synthesized image from the solid modeler is effectively utilized to verify the hypothesis computed from the edge information extracted from the observed image. To lessen the inefficiency of using the mathematical geometric method in the whole understanding process, a plane recognition process is introduced at an intermediate stage.>

It is pointed out that the degradation effect due to premodulation filtering in GMSK (Gaussian-filtered minimum shift keying) is largest at the edges of time slots, which instant has been adopted as the sample timing in the conventional coherent detector of GMSK. Then a new coherent detector employing signals sampled at a different timing in a deviated-frequency-locking scheme is presented to achieve a better bit-error-rate performance versus carrier-to-noise ratio.

Predetection Gaussian bandpass filtering effect on the coherent detection of minimum-shift-keying (MSK) is theoretically anlayzed on the basis of the worst signal pattern which brings the maximum intersymbol interference. The optimum 3 dB-down bandwidth (B)-bit duration (T) product of the Gaussian bandpass filter is proved theoretically to beBT = 0.5887, which degrades the requiredE_{b}/N_{0}(signal-energy-per-bit to noise-power-density ratio) only by 0.14 dB from that of antipodal coherent PSK using differential encoding. The degradations due to the phase errors of reference carrier and decision timing and the frequency drift of the received input signal are also shown. In addition, an alternative coherent detection using the reference carrier having the frequency deviated from the center frequency by the frequency deviation, which is called the deviated-frequency-locking scheme, is presented, and its error-rate performance is proved to be substantially identical with that of the conventional center-frequency-locking scheme.