Transforming a natural language (NL) question into a corresponding logical form (LF) is central to the knowledge-based question answering (KB-QA) task.Unlike most previous methods that achieve this goal based on mappings between lexicalized phrases and logical predicates, this paper goes one step further and proposes a novel embedding-based approach that maps NL-questions into LFs for KB-QA by leveraging semantic associations between lexical representations and KBproperties in the latent space.Experimental results demonstrate that our proposed method outperforms three KB-QA baseline methods on two publicly released QA data sets.

Millions of posts are being generated in real-time by users in social networking services, such as Twitter. However, a considerable number of those posts are mundane posts that are of interest to the authors and possibly their friends only. This paper investigates the problem of automatically discovering valuable posts that may be of potential interest to a wider audience. Specifically, we model the structure of Twitter as a graph consisting of users and posts as nodes and retweet relations between the nodes as edges. We propose a variant of the HITS algorithm for producing a static ranking of posts. Experimental results on real world data demonstrate that our method can achieve better performance than several baseline methods.

Traditional ranking models for information retrieval lack the ability to make a clear distinction between relevant and nonrelevant documents at top ranks if both have similar bag-of-words representations with regard to a user query. We aim to go beyond the bag-of-words approach to document ranking in a new perspective, by representing each document as a sequence of sentences. We begin with an assumption that relevant documents are distinguishable from nonrelevant ones by sequential patterns of relevance degrees of sentences to a query. We introduce the notion of relevance flow, which refers to a stream of sentence-query relevance within a document. We then present a framework to learn a function for ranking documents effectively based on various features extracted from their relevance flows and leverage the output to enhance existing retrieval models. We validate the effectiveness of our approach by performing a number of retrieval experiments on three standard test collections, each comprising a different type of document: news articles, medical references, and blog posts. Experimental results demonstrate that the proposed approach can improve the retrieval performance at the top ranks significantly as compared with the state-of-the-art retrieval models regardless of document type.

Opinion retrieval involves the measuring of opinion score of a document about the given topic. We propose a new method, namely sentiment-relevance flow, that naturally unifies the topic relevance and the opinionated nature of a document. Experiments conducted over a large-scaled Web corpus show that the proposed approach improves performance of opinion retrieval in terms of precision at top ranks.

Most traditional ranking models roughly score the relevance of a given document by observing simple term statistics, such as the occurrence of query terms within the document or within the collection. Intuitively, the relative importance of query terms with regard to other individual non-query terms in a document can also be exploited to promote the ranks of documents in which the query is dedicated as the main topic. In this paper, we introduce a simple technique named intra-document term ranking, which involves ranking all the terms in a document according to their relative importance within that particular document. We demonstrate that the information regarding the rank positions of given query terms within the intra-document term ranking can be useful for enhancing the precision of top-retrieved results by traditional ranking models. Experiments are conducted on three standard TREC test collections.

With the rise of digital video consumptions, contextual video advertising demands have been increasing in recent years. This paper presents a novel video advertising system that selects relevant text ads for a given video scene by automatically identifying the situation of the scene. The situation information of video scenes is inferred from available video scripts. Experimental results show that the use of the situation information enhances the accuracy of ad retrieval for video scenes. The proposed system represents one of the pioneer video advertising systems using contextual information obtained from video scripts.

A key to success to contextual in-video advertising is finding advertising keywords on video contents effectively, but there has been little literature in the area so far. This paper presents some preliminary results of our learning-based system that finds relevant advertising keywords on particular scene of video contents using their scripts. The system is trained with not only features proven useful in earlier studies but novel features that reflect the situation of a targeted scene. Experimental results show that the new features are potentially helpful for enhancing the accuracy of keyword extraction for contextual in-video advertising.

This paper proposes new probabilistic models for analyzing Korean morphology. In order to take advantage of the characteristics of Korean morphology, the proposed models are based on three linguistic units: eojeol (a Korean spacing unit), morpheme, and syllable. Unlike previous approaches that are based on rules and dictionaries, the probabilistic approach proposed in this study can automatically acquire complete linguistic knowledge from part-of-speech (POS) tagged corpora. In addition, this approach, without any system modification, is easily applicable to other corpora with different tag sets and annotation guidelines. The three different models and their combinations are evaluated on three corpora over a wide range of conditions. The eojeol-unit and syllable-unit models compensate for the weaknesses of the morpheme-unit model. The eojeol-unit model performed efficiently, and improved the precision. The syllable-unit model improved in precision as well, showing a particularly robust performance in treating unknown words. The proposed approach is also proven to outperform the previous approaches.

We present a Korean question answering framework for restricted domains, called K-QARD. K-QARD is developed to achieve domain portability and robustness, and the framework is successfully applied to build question answering systems for several domains.

This paper proposes a probabilistic model for definitional question answering (QA) that reflects the characteristics of the definitional question. The intention of the definitional question is to request the definition about the question target. Therefore, an answer for the definitional question should contain the content relevant to the topic of the target, and have a representation form of the definition style. Modeling the problem of definitional QA from both the topic and definition viewpoints, the proposed probabilistic model converts the task of answering the definitional questions into that of estimating the three language models: topic language model, definition language model, and general language model. The proposed model systematically combines several evidences in a probabilistic framework. Experimental results show that a definitional QA system based on the proposed probabilistic model is comparable to state-of-the-art systems.

In this paper, we present a two-phase biomedical NE-recognition method based on a ME model: we first recognize biomedical terms and then assign appropriate semantic classes to the recognized terms. In the two-phase NE-recognition method, the performance of the term-recognition phase is very important, because the semantic classification is performed on the region identified at the recognition phase. In this study, in order to improve the performance of term recognition, we try to incorporate lexical knowledge into pre- and postprocessing of the term-recognition phase. In the preprocessing step, we use domain-salient words as lexical knowledge obtained by corpus comparison. In the postprocessing step, we utilize χ 2 -based collocations gained from Medline corpus. In addition, we use morphological patterns extracted from the training data as features for learning the ME-based classifiers. Experimental results show that the performance of NE-recognition can be improved by utilizing such lexical knowledge.

While naive Bayes is quite effective in various data mining tasks, it shows a disappointing result in the automatic text classification problem. Based on the observation of naive Bayes for the natural language text, we found a serious problem in the parameter estimation process, which causes poor results in text classification domain. In this paper, we propose two empirical heuristics: per-document text normalization and feature weighting method. While these are somewhat ad hoc methods, our proposed naive Bayes text classifier performs very well in the standard benchmark collections, competing with state-of-the-art text classifiers based on a highly complex learning method such as SVM.

In this paper, we propose a feature-based Korean grammar utilizing the learned constraint rules in order to improve parsing efficiency. The proposed grammar consists of feature structures, feature operations, and constraint rules; and it has the following characteristics. First, a feature structure includes several features to express useful linguistic information for Korean parsing. Second, a feature operation generating a new feature structure is restricted to the binary-branching form which can deal with Korean properties such as variable word order and constituent ellipsis. Third, constraint rules improve efficiency by preventing feature operations from generating spurious feature structures. Moreover, these rules are learned from a Korean treebank by a decision tree learning algorithm. The experimental results show that the feature-based Korean grammar can reduce the number of candidates by a third of candidates at most and it runs 1.5 ∼ 2 times faster than a CFG on a statistical parser.

In this paper, we present a syllable-based probabilistic morphological analysis model of Korean. While the pre-viousmorphological analyzers that regardmorpheme as a processing unit, the model exploits syllable as a process-ing unit in order to endure the unknown word problem. Actually, it does not use any morpheme dictionary. In contract to the previous systems that depend on manually constructed linguistic knowledge, the proposed system can fully automatically acquire the linguistic knowledge from annotated corpora. Besides, without any modifica-tion, the system can be applied to other corpus having a different tagset and annotation guidelines. We describe the model and present experimental results on two cor-pora. 1.

Information retrieval using word senses is emerging as a good research challenge on semantic information retrieval. In this paper, we propose a new method using word senses in information retrieval: root sense tagging method. This method assigns coarse-grained word senses defined in WordNet to query terms and document terms by unsupervised way using co-occurrence information constructed automatically. Our sense tagger is crude, but performs consistent disambiguation by considering only the single most informative word as evidence to disambiguate the target word. We also allow multiple-sense assignment to alleviate the problem caused by incorrect disambiguation.Experimental results on a large-scale TREC collection show that our approach to improve retrieval effectiveness is successful, while most of the previous work failed to improve performances even on small text collection. Our method also shows promising results when is combined with pseudo relevance feedback and state-of-the-art retrieval function such as BM25.

This paper presents a method to develop a class of variable memory Markov models that have higher memory capacity than traditional (uniform memory) Markov models. The structure of the variable memory models is induced from a manually annotated corpus through a decision tree learning algorithm. A series of comparative experiments show the resulting models outperform uniform memory Markov models in a part-of-speech tagging task.

Noun extraction is very important for many NLP applications such as information retrieval, automatic text classification, and information extraction. Most of the previous Korean noun extraction systems use a morphological analyzer or a Part-of-Speech (POS) tagger. Therefore, they require much of the linguistic knowledge such as morpheme dictionaries and rules (e.g. morphosyntactic rules and morphological rules).This paper proposes a new noun extraction method that uses the syllable based word recognition model. It finds the most probable syllable-tag sequence of the input sentence by using automatically acquired statistical information from the POS tagged corpus and extracts nouns by detecting word boundaries. Furthermore, it does not require any labor for constructing and maintaining linguistic knowledge. We have performed various experiments with a wide range of variables influencing the performance. The experimental results show that without morphological analysis or POS tagging, the proposed method achieves comparable performance with the previous methods.

Multinomial naive Bayes classifiers have been widely used for the probabilistic text classification. However, their parameter estimation method sometimes generates inappropriate probabilities. In this paper, we propose a topic document model approach for naive Bayes text classification, where their parameters are estimated with an expectation from the training documents. Experiments are conducted on Reuters 21578 and 20 Newsgroup collection, and our proposed approach obtained a significant improvement in performace over the conventional approach.

In this paper we present part-of-speech taggers based on hidden Markov models, which adopt a less strict Markov assumption to consider rich contexts. In models whose parameters are very specific like lexicalized ones, sparse-data problem is very serious and also conditional probabilities tend to be estimated unreliably. To overcome data-sparseness, a simplified version of the well-known back-off smoothing method is used. To mitigate unreliable estimation problem, our models assume joint independence instead of conditional independence because joint probabilities have the same degree of estimation reliability. In experiments for the Brown corpus, models with rich contexts achieve relatively high accuracy and some models assuming joint independence show better results than the corresponding HMMs.

&% ' )( * '+ -, .! !/ 10 2 3 4 4 5 6 74 8 ) 7 9 !: ; 74 < 64 )0 >= ?4 4 ) ;@ -% 9 ; 7 A% 9 B C % ED F HG -'+ -, 7 / ! ; 74 -F H " 7 JI K ML C / N " 8 A% 9 -% ED O QP R !S 9T VU XW MW ZY [ '[ ]\ _9ba Mc R NT ed gf h d 5i kj lc m nd od p 7q Vr \ _s ;t *u q vt w _x Xy B&x zw _s *u 3\ t e{ |w E^} V{ q & q 9{ | q s * ;{ |t B w x A w E v Ew w E9 Ew 3 B _ 9 5 9& ' _w B ' w E v Ew E B E E E 9 E\ r \ _^ q nq t * * ;{ |{ o 7{ V V t ew E v _w 9 ¡\ _ r ¢ P 9[ ET ¤£ ¥h !P R !S §¦ d g¨ p 7q nr \ s ;t eu q vt ©w _x Xª 5w Eu r &t q s ©} n{ q 9

A new model named Boolean Latent Semantic Indexing model based on the Singular Value Decomposition and Boolean query formulation is introduced. While the Singular Value Decomposition alleviates the problems of lexical matching in the traditional information retrieval model, Boolean query formulation can help users to make precise representation of their information search needs. Retrieval experiments on a number of test collections seem to show that the proposed model achieves substantial performance gains over the Latent Semantic Indexing model.

Korean compound nouns may be written as a sequence of characters without blanks between unit nouns. For Korean processing systems, Korean compound nouns have to be first segmented into a sequence of unit nouns. However, the segmentation task is difficult because a sequence of characters may be ambiguously segmented to several sequences of appropriate unit nouns. Moreover, this task is not trivial because Korean compound nouns may include many unknown unit nouns. This paper proposes a new method for KCNS (Korean Compound Noun Segmentation) and reports on the appliccation of such a segmentationtechnique to enhance the performance of an information retrieval system. According to our method, compound nouns are first segmented by using a dictionary and structure patterns. If they are ambiguously segmented, we resolve the ambiguities by using statistical information and a preference rule. Moreover, we employ three kinds of heuristics in order to segment compound nouns with unknown unit nouns. To evaluate KCNS, we use three kinds of data from various domains. Experimental results show that the precision of KCNS's output is approximately 96% on average, regardless of domains. The effectiveness of using the segmented unit nouns provided by KCNS for indexing is proved by improving retrieval performance of our information retrieval system.

This paper includes a description of 3 affiliated oriental languages: Chinese, Japanese, and Korean. It includes a description of the origins of these 3 languages and the inter-relationship among them. Drawn from the viewpoints of several experienced researchers in the field of OCR (Optical Character Recognition) and computational linguistics, it attempts to bring out the intriguing aspects of these 3 ideographic languages, including the formation and composition of pictograms, special features, learning, understanding, contextual information, and recognition of characters and words, and their relations to poetic expressions and pattern recognition techniques. Numerous references are given and comments on future trends are also presented.

In this paper, we present a computational method for transforming a syntactic graph, which represents all syntactic interpretations of a sentence, into a semantic graph which filters out certain interpretations, but also incorporates any remaining ambiguities. We argue that the resulting ambiguous graph, supported by an exclusion matrix, is a useful data structure for question answering and other semantic processing. Our research is based on the principle that ambiguity is an inherent aspect of natural language communication.