Logic-Based Question Answering

Furbach, Ulrich; Glöckner, Ingo; Helbig, Hermann; Pelzer, Björn

doi:10.1007/s13218-010-0010-x

Cited by 13 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a consequence, these representations are often utilised in distinct applications. For example, logic based representations have been successful in natural language database querying systems (Thompson et al, 1997), question answering (Furbach et al, 2010;Moldovan et al, 2003) and natural language interfaces for robot control (Ge and Mooney, 2009). On the other hand, distributional models have been applied to essay grading (Landauer et al, 1997), word sense discrimination (Schütze, 1998), ontology extraction (Yamada et al, 2009) and modelling semantic priming (Lund and Burgess, 1996;Landuaer and Dumais, 1997).…”

Section: Theories and Models Of Semanticsmentioning

confidence: 99%

Composition in Distributional Models of Semantics

2010

View full text Add to dashboard Cite

Distributional models of semantics have proven themselves invaluable both in cognitive modelling of semantic phenomena and also in practical applications. For example, they have been used to model judgments of semantic similarity (McDonald, 2000) and association (Denhire and Lemaire, 2004;Griffiths et al., 2007) and have been shown to achieve human level performance on synonymy tests (Landuaer and Dumais, 1997;Griffiths et al., 2007) such as those included in the Test of English as Foreign Language (TOEFL). This ability has been put to practical use in automatic thesaurus extraction (Grefenstette, 1994). However, while there has been a considerable amount of research directed at the most effective ways of constructing representations for individual words, the representation of larger constructions, e.g., phrases and sentences, has received relatively little attention. In this thesis we examine this issue of how to compose meanings within distributional models of semantics to form representations of multi-word structures.Natural language data typically consists of such complex structures, rather than just individual isolated words. Thus, a model of composition, in which individual word meanings are combined into phrases and phrases combine to form sentences, is of central importance in modelling this data. Commonly, however, distributional representations are combined in terms of addition (Landuaer and Dumais, 1997;Foltz et al., 1998), without any empirical evaluation of alternative choices. Constructing effective distributional representations of phrases and sentences requires that we have both a theoretical foundation to direct the development of models of composition and also a means of empirically evaluating those models.The approach we take is to first consider the general properties of semantic composition and from that basis define a comprehensive framework in which to consider the composition of distributional representations. The framework subsumes existing proposals, such as addition and tensor products, but also allows us to define novel composition functions. We then show that the effectiveness of these models can be i evaluated on three empirical tasks.The first of these tasks involves modelling similarity judgements for short phrases gathered in human experiments. Distributional representations of individual words are commonly evaluated on tasks based on their ability to model semantic similarity relations, e.g., synonymy or priming. Thus, it seems appropriate to evaluate phrase representations in a similar manner. We then apply compositional models to language modelling, demonstrating that the issue of composition has practical consequences, and also providing an evaluation based on large amounts of natural data. In our third task, we use these language models in an analysis of reading times from an eye-movement study. This allows us to investigate the relationship between the composition of distributional representations and the processes involved in comprehending phrases and sentences.We ...

show abstract

Section: Theories and Models Of Semanticsmentioning

confidence: 99%

Composition in Distributional Models of Semantics

2010

View full text Add to dashboard Cite

show abstract

“…Mihalcea (2007, p.196) describe "a method for generating sense-tagged data using Wikipedia as a source of sense annotations." The esul s o he expe men s es gne n h s s u y showe " h he W k pese sense nno ons e el le n c n e use o cons uc ccu e sense cl ss e s." Furbach et al (2010) esc e LogAnswe , " Ge m n l ngu ge ques on nswe ng sys em wh ch com nes computational linguistics and automated reasoning to deduce answers from a knowledge base derived om W k pe " (2010, p.51). A semantic network representation of a snapshot of the German Wikipedia and 12,000 logical rules were used as the knowledge base of the system.…”

Section: Computational Linguisticsmentioning

confidence: 99%

The People’s Encyclopedia Under the Gaze of the Sages: A Systematic Review of Scholarly Research on Wikipedia

et al. 2012

View full text Add to dashboard Cite

Wikipedia has become one of the ten most visited sites on the Web, and the world's leading source of Web reference information. Its rapid success has inspired hundreds of scholars from various disciplines to study its content, communication and community dynamics from various perspectives. This article presents a systematic review of scholarly research on Wikipedia. We describe our detailed, rigorous methodology for identifying over 450 scholarly studies of Wikipedia. We present the WikiLit website (http://wikilit.referata.com), where most of the papers reviewed here are described in detail. In the major section of this article, we then categorize and summarize the studies. An appendix features an extensive list of resources useful for Wikipedia researchers.

show abstract

“…They argued for Wikipedia's suitability for such methods because of its structured document network and varied types of pages such as disambiguation and redirection pages. Furbach et al [39] described LogAnswer, a German language system that answers questions using Wikipedia's knowledge base derived by computational linguistics and automated reasoning means. A semantic network representation of a snapshot of the German Wikipedia and 12, 000 logical rules were used as the knowledge base of the system.…”

Section: Natural Language Processingmentioning

confidence: 99%

Excavating the mother lode of human-generated text: A systematic review of research that uses the wikipedia corpus

Mehdi

Okoli

Mesgari

et al. 2017

Information Processing & Management

View full text Add to dashboard Cite

Although primarily an encyclopedia, Wikipedia's expansive content provides a knowledge base that has been continuously exploited by researchers in a wide variety of domains. This article systematically reviews the scholarly studies that have used Wikipedia as a data source, and investigates the means by which Wikipedia has been employed in three main computer science research areas: information retrieval, natural language processing, and ontology building. We report and discuss the research trends of the identified and examined studies. We further identify and classify a list of tools that can be used to extract data from Wikipedia, and compile a list of currently available data sets extracted from Wikipedia.

show abstract

Logic-Based Question Answering

Cited by 13 publications

References 10 publications

Composition in Distributional Models of Semantics

Composition in Distributional Models of Semantics

The People’s Encyclopedia Under the Gaze of the Sages: A Systematic Review of Scholarly Research on Wikipedia

Excavating the mother lode of human-generated text: A systematic review of research that uses the wikipedia corpus

Contact Info

Product

Resources

About