Modern systems that deal with inference in texts need automatized methods to extract meaning representations (MRs) from texts at scale. Open Information Extraction (IE) is a prominent way of extracting all potential relations from a given text in a comprehensive manner. Previous work in this area has mainly focused on the extraction of isolated relational tuples. Ignoring the cohesive nature of texts where important contextual information is spread across clauses or sentences, state-of-the-art Open IE approaches are thus prone to generating a loose arrangement of tuples that lack the expressiveness needed to infer the true meaning of complex assertions. To overcome this limitation, we present a method that allows existing Open IE systems to enrich their output with additional meta information. By leveraging the semantic hierarchy of minimal propositions generated by the discourse-aware Text Simplification (TS) approach presented in Niklaus et al. (2019), we propose a mechanism to extract semantically typed relational tuples from complex source sentences. Based on this novel type of output, we introduce a lightweight semantic representation for Open IE in the form of normalized and context-preserving relational tuples. It extends the shallow semantic representation of state-of-the-art approaches in the form of predicate-argument structures by capturing intra-sentential rhetorical structures and hierarchical relationships between the relational tuples. In that way, the semantic context of the extracted tuples is preserved, resulting in more informative and coherent predicate-argument structures which are easier to interpret. In addition, in a comparative analysis, we show that the semantic hierarchy of minimal propositions benefits Open IE approaches in a second dimension: the canonical structure of the simplified sentences is easier to process and analyze, and thus facilitates the extraction of relational tuples, resulting in an improved precision (up to 32%) and recall (up to 30%) of the extracted relations on a large benchmark corpus.

In linguistics, there are two main perspectives on negation: a semantic and a pragmatic view.So far, research in NLP on negation has almost exclusively adhered to the semantic view.In this article, we adopt the pragmatic paradigm to conduct a study of negation understanding focusing on transformer-based PLMs.Our results differ from previous, semantics-based studies and therefore help to contribute a more comprehensive -and, given the results, much more optimistic -picture of the PLMs' negation understanding.

Thiemo Wambsganss, Christina Niklaus, Matthias Söllner, Siegfried Handschuh, Jan Marco Leimeister. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Recent advances in Natural Language Processing (NLP) bear the opportunity to analyze the argumentation quality of texts. This can be leveraged to provide students with individual and adaptive feedback in their personal learning journey. To test if individual feedback on students' argumentation will help them to write more convincing texts, we developed AL, an adaptive IT tool that provides students with feedback on the argumentation structure of a given text. We compared AL with 54 students to a proven argumentation support tool. We found students using AL wrote more convincing texts with better formal quality of argumentation compared to the ones using the traditional approach. The measured technology acceptance provided promising results to use this tool as a feedback application in different learning settings. The results suggest that learning applications based on NLP may have a beneficial use for developing better writing and reasoning for students in traditional learning settings.

In this paper, we present a novel annotation approach to capture claims and premises of arguments and their relations in student-written persuasive peer reviews on business models in German language.We propose an annotation scheme based on annotation guidelines that allows to model claims and premises as well as support and attack relations for capturing the structure of argumentative discourse in student-written peer reviews.We conduct an annotation study with three annotators on 50 persuasive essays to evaluate our annotation scheme.The obtained interrater agreement of α = 0.57 for argument components and α = 0.49 for argumentative relations indicates that the proposed annotation scheme successfully guides annotators to moderate agreement.Finally, we present our freely available corpus of 1,000 persuasive student-written peer reviews on business models and our annotation guidelines to encourage future research on the design and development of argumentative writing support systems for students.

Recognizing textual entailment is a key task for many semantic applications, such as Question Answering, Text Summarization, and Information Extraction, among others. Entailment scenarios can range from a simple syntactic variation to more complex semantic relationships between pieces of text, but most approaches try a one-size-fits-all solution that usually favors some scenario to the detriment of another. We propose a composite approach for recognizing text entailment which analyzes the entailment pair to decide whether it must be resolved syntactically or semantically. We also make the answer interpretable: whenever an entailment is solved semantically, we explore a knowledge base composed of structured lexical definitions to generate natural language humanlike justifications, explaining the semantic relationship holding between the pieces of text. Besides outperforming wellestablished entailment algorithms, our composite approach gives an important step towards Explainable AI, using world knowledge to make the semantic reasoning process explicit and understandable.

We present an approach for recursively splitting and rephrasing complex English sentences into a novel semantic hierarchy of simplified sentences, with each of them presenting a more regular structure that may facilitate a wide variety of artificial intelligence tasks, such as machine translation (MT) or information extraction (IE).Using a set of hand-crafted transformation rules, input sentences are recursively transformed into a twolayered hierarchical representation in the form of core sentences and accompanying contexts that are linked via rhetorical relations.In this way, the semantic relationship of the decomposed constituents is preserved in the output, maintaining its interpretability for downstream applications.Both a thorough manual analysis and automatic evaluation across three datasets from two different domains demonstrate that the proposed syntactic simplification approach outperforms the state of the art in structural text simplification.Moreover, an extrinsic evaluation shows that when applying our framework as a preprocessing step the performance of state-of-the-art Open IE systems can be improved by up to 346% in precision and 52% in recall.To enable reproducible research, all code is provided online.

We introduce DisSim, a discourse-aware sentence splitting framework for English and German whose goal is to transform syntactically complex sentences into an intermediate representation that presents a simple and more regular structure which is easier to process for downstream semantic applications. For this purpose, we turn input sentences into a two-layered semantic hierarchy in the form of core facts and accompanying contexts, while identifying the rhetorical relations that hold between them. In that way, we preserve the coherence structure of the input and, hence, its interpretability for downstream tasks.

We compiled a new sentence splitting corpus that is composed of 203K pairs of aligned complex source and simplified target sentences.Contrary to previously proposed text simplification corpora, which contain only a small number of split examples, we present a dataset where each input sentence is broken down into a set of minimal propositions, i.e. a sequence of sound, self-contained utterances with each of them presenting a minimal semantic unit that cannot be further decomposed into meaningful propositions.This corpus is useful for developing sentence splitting approaches that learn how to transform sentences with a complex linguistic structure into a fine-grained representation of short sentences that present a simple and more regular structure which is easier to process for downstream applications and thus facilitates and improves their performance.

Building natural language programming systems that are geared towards end-users requires the abstraction of formalisms inherently introduced by programming languages, capturing the intent of natural language inputs and mapping it to existing programming language constructs.

Text entailment, the task of determining whether a piece of text logically follows from another piece of text, has become an important component for many natural language processing tasks, such as question answering and information retrieval. For entailments requiring world knowledge, most systems still work as a "black box," providing a yes/no answer that doesn't explain the reasoning behind it. We propose an interpretable text entailment approach that, given a structured definition graph, uses a navigation algorithm based on distributional semantic models to find a path in the graph which links text and hypothesis. If such path is found, it is used to provide a human-readable justification explaining why the entailment holds. Experiments show that the proposed approach present results comparable to some well-established entailment algorithms, while also meeting Explainable AI requirements, supplying clear explanations which allow the inference model interpretation.

We present an Open Information Extraction (IE) approach that uses a two-layered transformation stage consisting of a clausal disembedding layer and a phrasal disembedding layer, together with rhetorical relation identification. In that way, we convert sentences that present a complex linguistic structure into simplified, syntactically sound sentences, from which we can extract propositions that are represented in a two-layered hierarchy in the form of core relational tuples and accompanying contextual information which are semantically linked via rhetorical relations. In a comparative evaluation, we demonstrate that our reference implementation Graphene outperforms state-of-the-art Open IE systems in the construction of correct n-ary predicate-argument structures. Moreover, we show that existing Open IE approaches can benefit from the transformation process of our framework.

We provide a detailed overview of the various approaches that were proposed to date to solve the task of Open Information Extraction. We present the major challenges that such systems face, show the evolution of the suggested approaches over time and depict the specific issues they address. In addition, we provide a critique of the commonly applied evaluation procedures for assessing the performance of Open IE systems and highlight some directions for future work.

The ageing of the human population is a threat to many countries in the world and this fact creates new challenges for age-friendly living, recreational and working environments. Therefore, solutions that can support senior citizens (Longinos for the men and Longinas for the women) will be necessary, in order to help them stay actively involved in their professional life for longer. This is possible by designing fit for purpose working environments and by enabling flexible management of job-, leisure- and health-related activities, considering their needs at the workplace, at home and on the move, with a particular focus on fighting social isolation. This project presents a robotic digital solution that makes provision for Longinos/Longinas persons, that are above 70 years old, a single view of integrated health, business and social data spread respectively in online health communities, online project management websites and social networks, as well as the provision of a set of services, that will allow them to manage huge amounts of data.

Different semantic interpretation tasks such as text entailment and question answering require the classification of semantic relations between terms or entities within text. However, in most cases, it is not possible to assign a direct semantic relation between entities/terms. This paper proposes an approach for composite semantic relation classification using one or more relations between entities/term mentions, extending the traditional semantic relation classification task . The proposed model is different from existing approaches which typically use machine learning models built over lexical and distributional word vector features in that is uses a combination of a large commonsense knowledge base of binary relations , a distributional navigational algorithm and sequence classification to provide a solution for the composite semantic relation classification problem. The proposed approach outperformed existing baselines with regard to F1-score, Accuracy, Precision and Recall.

This demonstration presents an infrastructure for computing multilingual semantic relatedness and correlation for twelve natural languages by using three distributional semantic models (DSMs). Our demonsrator - DInfra (Distributional Infrastructure) provides researchers and developers with a highly useful platform for processing large-scale corpora and conducting experiments with distributional semantics. We integrate several multilingual DSMs in our webservice so end user can obtain a result without worrying about the complexities involved in building DSMs. Our webservice allows the users to have easy access to a wide range of comparisons of DSMs with different parameters. In addition, users can configure and access DSM parameters using a easy to use API.

Entering 'Football Players from United States' when searching for 'American Footballers' is an example of vocabulary mismatch, which occurs when different words are used to express the same concepts. In order to address this phenomenon for entity search targeting descriptors for complex categories, we propose a compositional-distributional semantics entity search engine, which extracts semantic and commonsense knowledge from large-scale corpora to address the vocabulary gap between query and data.

Vector space models (VSMs) are mathematically well-defined frameworks that have been widely used in the distributional approaches to semantics. In VSMs, high-dimensional vectors represent linguistic entities. In an application, the similarity of vectors and thus the entities that they represent is computed by a distance formula. The high dimensionality of vectors, however, is a barrier to the performance of methods that employ VSMs. Consequently, a dimensionality reduction technique is employed to alleviate this problem. This paper introduces a novel technique called Random Manhattan Indexing (RMI) for the construction of L1 normed VSMs at reduced dimensionality. RMI combines the construction of a VSM and dimension reduction into an incremental and thus scalable two-step procedure. In order to attain its goal, RMI employs the sparse Cauchy random projections. We further introduce Random Manhattan Integer Indexing (RMII): a computationally enhanced version of RMI. As shown in the reported experiments, RMI and RMII can be used reliably to estimate the L1 distances between vectors in a vector space of low dimensionality.

Faceted navigation is a technique for the exploration and discovery of a collection of resources, which can be of various types including text documents. While being information-rich resources, documents are usually not treated as content-bearing items in faceted browsing interfaces, and yet the required clean metadata is not always available or matches users’ interest. In addition, the existing linear listing paradigm for representing result items from the faceted filtering process makes it difficult for users to traverse or compare across facet values in different orders of importance to them. In this context, we report in this article a visual support toward faceted browsing of a collection of documents based on a set of entities of interest to users. Our proposed approach involves using a multi-dimensional visualization as an alternative to the linear listing of focus items. In this visualization, visual abstraction based on a combination of a conceptual structure and the structural equivalence of documents can be simultaneously used to deal with a large number of items. Furthermore, the approach also enables visual ordering based on the importance of facet values to support prioritized, cross-facet comparisons of focus items. A user study was conducted and the results suggest that interfaces using the proposed approach can support users better in exploratory tasks and were also well-liked by the participants of the study, with the hybrid interface combining the multi-dimensional visualization with the linear listing receiving the most favorable ratings.

With the advent of online social networks and User-Generated Content (UGC), the social Web is experiencing an explosion of audio-visual data. However, the usefulness of the collected data is in doubt, given that the means of retrieval are limited by the semantic gap between them and people’s perceived understanding of the memories they represent. Whereas machines interpret UGC media as series of binary audio-visual data, humans perceive the context under which the content is captured and the people, places, and events represented. The Annotation CReatiON for Your Media (ACRONYM) framework addresses the semantic gap by supporting the creation of a layer of explicit machine-interpretable meaning describing UGC context. This paper presents an overview of a use case of ACRONYM for semantic annotation of personal photographs. The authors define a set of recommendation algorithms employed by ACRONYM to support the annotation of generic UGC multimedia. This paper introduces the context metrics and combination methods that form the recommendation algorithms used by ACRONYM to determine the people represented in multimedia resources. For the photograph annotation use case, these result in an increase in recommendation accuracy. Context-based algorithms provide a cheap and robust means of UGC media annotation that is compatible with and complimentary to content-recognition techniques.

The classic TileBars paradigm has been used to show distribution information of query terms in full-text documents. However, when used to show the distribution of a large number of entities of interest to users within a document, it hinders users' quick comprehension due to the inherent visual complexity problem. In this paper, we present a novel approach to improve the visual presentation of TileBars, in which barycenter heuristic for bigraph crossing minimization is used to reorder TileBars' elements. The reordered TileBars enables users to quickly and easily identify which entities appear in the beginning, end, or throughout a document. A user study has shown that the reordered TileBars can provide users with better focus and navigation while exploring text documents.

Presence management, i.e., the ability to automatically identify the status and availability of communication partners, is becoming an invaluable tool for collaboration in enterprise contexts. In this paper, we argue for efficient presence management by means of a holistic view of both physical cont

Recent innovations in the Social and Semantic Web fields have resulted in large amounts of data created, published and consumed by users of the Web. This vast amount of data exists in a variety of formats, from the traditional ones such as text, image, video to the more recent additions such as streams of status information from Twitter and Facebook. The ability to easily integrate such vast amounts of data raises significant and exciting research challenges, not least of which how to provide effective access to and navigation across heterogeneous data sources on different platforms (e.g. computers, mobile devices, set-top boxes). Building on the success of the VISSW2009 workshop, the IUI2010 workshop on Visual Interfaces to the Social and Semantic Web aims to bring together researchers and practitioners from different fields to discuss the latest research results and challenges in designing, implementing, and evaluating intelligent interfaces supporting access, navigation and publishing of different types of contents on the Social and Semantic Web. This paper outlines the context of the workshop and provides an overview of the research to be presented at the event.

Richly interlinked metadata constitute the foundation of the Semantic Web. Manual semantic annotation is a labor intensive task requiring training in formal ontological descriptions for the otherwise non-expert user. Although automatic annotation tools attempt to ease this knowledge acquisition barrier, their development often requires access to specialists in Natural Language Processing (NLP). This challenges researchers to develop user-friendly annotation environments. Controlled Natural Languages (CNLs) offer an incentive to the novice user to annotate, while simultaneously authoring his/her respective documents in a user-friendly manner. CNLs have been successfully applied to ontology authoring, but little research has focused on their application to semantic annotation. This paper describes two novel approaches to semantic annotation, which permit non-expert users to simultaneously author and annotate meeting minutes using CNL. Finally, this work provides empirical evidence that for certain scenarios applying CNLs for semantic annotation can be more user friendly than a standard manual semantic annotation tool.

Using the current state of the art in life science publication search (e.g., PubMed), one can efficiently search for resources containing particular key-words or their combinations. It is impossible to search for abstract concepts and expressive relations between them (e.g., type of, different from or part of), though. Nevertheless, such a more expressive - semantic - search could largely reduce the efforts related to finding appropriate answers in biomedical articles. In this paper we identify challenges related to building a semantic publication search engine. Then we describe the architecture and usage principles of a tool tackling them. Eventually, we report on the tool's deployment on oncological literature data and preliminary tests with domain experts.

Recent developments in the Social and Semantic Web fields have resulted in large amounts of data created, published and consumed by users of the Web. The ability to easily integrate such vast amounts of data raises significant and exciting research challenges, not least of which how to provide effective access to and navigation across heterogeneous data sources. The IUI2009 workshop on Visual Interfaces to the Social and the Semantic Web aims to bring together researchers and practitioners from different fields to discuss the latest research results and challenges in designing, implementing, and evaluating intelligent interfaces supporting access, navigation and publishing of different types of contents on the Social and Semantic Web. This paper outlines the context of the workshop and provides an overview of the research to be presented at the event.

In this paper we present IVEA, a personalized visual interface which enables users to explore text collections from different perspectives and levels of detail. This work explores the use of a personal ontology, which encapsulates users' entities of interest, as an anchor for the exploration process. This, in effect, simplifies the comprehension of visual representation of text collections by helping users to focus on aspects that they are particularly concerned with.

In this paper, we present an interactive matrix-based multi-dimensional visualization component which enables the users to explore a text collection along different conceptual dimensions. Of importance in our approach are the tight coupling of the users' personal ontologies representing their spheres of interest with the visualization component and the application of barycenter heuristic for edge crossing minimization to enhance its visual display. We also discuss how IVEA, the information visualization tool containing the proposed component, can address the commonly perceived constraints of building a personal ontology from scratch for IVEA to work.

Classic argumentative discussions can be found in a variety of domains from traditional scientific publishing to today's modern social software. An interactive argumentative discussion usually consists of an initial proposition stated by a single creator, followed by supporting propositions or counter-propositions from other contributors. Thus, the actual argumentation semantics is hidden in the content created by the contributors. Although there are approaches that try to deal with this challenge, most of them focus on a particular domain, limiting the scope of the argumentation to that domain only. In this paper, we describe an abstract model for argumentation which captures the semantics independently of the domain. Following a modularized approach, we also take into account additional important aspects of the argumentation, like the provenance information or its evolution (the temporal side).

In this paper we present the SALT (Semantically Annotated LATEX) Triple, a set of tools built to demonstrate a complete annotation workflow from creation to usage. The Triple set contains the authoring and annotation framework, an editor and a web publisher which helps the generation or uses the generated metadata for a specific purpose. The demos show three phases part of the workflow: (i) authoring -- first we introduce the way in which concurrent annotations can be created during the authoring process by using the iSALT editor as a front-end for the SALT framework; (ii) generation -- then we show how the metadata is generated and embedded into the final result of the authoring and annotation proces, i.e. a semantically enriched PDF document; (iii) usage -- and finally we demostrate a way how the metadata can be used for generating a set of rich online workshop proceedings.

The structure of a document has an important influence on the perception of its content. Considering scientific publications, we can affirm that by making use of the ordinary linear layout, a well organized publication, following a "red wire", will always be better understood and analyzed than one having a poor or chaotic structure, but not necessarily poor content. Reading a publication in a linear way, from the first page to the last page means a lot of unnecessary information processing to the reader. Looking at a publication from another perspective by accessing the key-points or argumentative structure directly can give better insights into the author's thoughts, and for certain tasks (i.e. getting a first impression of an article) a representation of the document reduced to its core could be more important than its linear structure. In this paper, we will show how one can build different representations of the same document, by exploiting the semantics captured in the text. The focus will be on scientific publications and as building foundation we use the SALT (Semantically Annotated LATEX) annotation framework for creating Semantic PDF Documents.

The success of the Semantic Web depends on the availability of Web pages annotated with metadata. Free form metadata or tags, as used in social bookmarking and folksonomies, have become more and more popular and successful. Such tags are relevant keywords associated with or assigned to a piece of information (e.g., a Web page), describing the item and enabling keyword-based classification. In this paper we propose P-TAG, a method which automatically generates personalized tags for Web pages. Upon browsing a Web page, P-TAG produces keywords relevant both to its textual content, but also to the data residing on the surfer's Desktop, thus expressing a personalized viewpoint. Empirical evaluations with several algorithms pursuing this approach showed very promising results. We are therefore very confident that such a user oriented automatic tagging approach can provide large scale personalized metadata annotations as an important step towards realizing the Semantic Web.

The success of the Semantic Web depends on the availability of ontologies as well as on the proliferation of web pages annotated with metadata conforming to these ontologies. Thus, a crucial question is where to acquire these metadata from. In this paper wepropose PANKOW (Pattern-based Annotation through Knowledge on theWeb), a method which employs an unsupervised, pattern-based approach to categorize instances with regard to an ontology. The approach is evaluated against the manual annotations of two human subjects. The approach is implemented in OntoMat, an annotation tool for the Semantic Web and shows very promising results.

The success of the Semantic Web crucially depends on the easy creation, integration and use of semantic data. For this purpose, we consider an integration scenario that defies core assumptions of current metadata construction methods. We describe a framework of metadata creation when web pages are generated from a database and the database owner is cooperatively participating in the Semantic Web. This leads us to the definition of ontology mapping rules by manual semantic annotation and the usage of the mapping rules and of web services for semantic queries. In order to create metadata, the framework combines the presentation layer with the data description layer -- in contrast to "conventional" annotation, which remains at the presentation layer. Therefore, we refer to the framework as deep annotation 1.We consider deep annotation as particularly valid because, (i), web pages generated from databases outnumber static web pages, (ii), annotation of web pages may be a very intuitive way to create semantic data from a database and, (iii), data from databases should not be materialized as RDF files, it should remain where it can be handled most efficiently -- in its databases.

Richly interlinked, machine-understandable data constitute the basis for the Semantic Web. We provide a framework, CREAM, that allows for creation of metadata. While the annotation mode of CREAM allows to create metadata for existing web pages, the authoring mode lets authors create metadata --- almost for free --- while putting together the content of a page.As a particularity of our framework, CREAM allows to create relational metadata, i.e. metadata that instantiate interrelated definitions of classes in a domain ontology rather than a comparatively rigid template-like schema asm Dublin Core. We discuss some of the requirements one has to meet when developing such an ontology-based framework, e.g. the integration of a metadata crawler, inference services, document management and a meta-ontology, and describe its implementation, viz. Ont-O-Mat, a component-based, ontology-driven Web page authoring and annotation tool.

Richly interlinked, machine-understandable data constitutes the basis for the Semantic Web. Annotating web documents is one of the major techniques for creating metadata on the Web. However, annotation tools so far are restricted in their capabilities of providing richly interlinked and truely machine-understandable data. They basically allow the user to annotate with plain text according to a template structure, such as Dublin Core. We here present CREAM (Creating RElational, Annotation-based Metadata), a framework for an annotation environment that allows to construct relational metadata, i.e. metadata that comprises class instances and relationship instances. These instances are not based on a fix structure, but on a domain ontology. We discuss some of the requirements one has to meet when developing such a framework, e.g. the integration of a metadata crawler, inference services, document management and information extraction, and describe its implementation, viz. Ont-O-Mat a component-based, ontology-driven annotation tool.

The WWW is the most important resource for external business information. This paper presents a tool called INSYDER, an information assistant for finding and analysis business information from the WWW. INSYDER is a system using different agents for crawling the Web, evaluating and visualising the results. These agents, the used visualisations, and a first summary of user studies are presented.