An application of automated reasoning in natural language question answering

Furbach, Ulrich; Glöckner, Ingo; Pelzer, Björn

doi:10.3233/aic-2010-0461

Cited by 28 publications

(21 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LogAnswer [8,9] is an open-domain question answering system, accessible via a web interface (www.loganswer. de) similar to that of a search engine.…”

Section: Deep Question Answering and The Loganswer Systemmentioning

confidence: 99%

The RatioLog Project: Rational Extensions of Logical Reasoning

et al. 2015

Self Cite

View full text Add to dashboard Cite

Higher-level cognition includes logical reasoning and the ability of question answering with common sense. The RatioLog project addresses the problem of rational reasoning in deep question answering by methods from automated deduction and cognitive computing. In a first phase, we combine techniques from information retrieval and machine learning to find appropriate answer candidates from the huge amount of text in the German version of the free encyclopedia "Wikipedia". In a second phase, an automated theorem prover tries to verify the answer candidates on the basis of their logical representations. In a third phase -because the knowledge may be incomplete and inconsistent -, we consider extensions of logical reasoning to improve the results. In this context, we work toward the application of techniques from human reasoning: We employ defeasible reasoning to compare the answers w.r.t. specificity, deontic logic, normative reasoning, and model construction. Moreover, we use integrated case-based reasoning and machine learning techniques on the basis of the semantic structure of the questions and answer candidates to learn giving the right answers.

show abstract

“…LogAnswer [8,9] is an open-domain question answering system, accessible via a web interface (www.loganswer. de) similar to that of a search engine.…”

Section: Deep Question Answering and The Loganswer Systemmentioning

confidence: 99%

The RatioLog Project: Rational Extensions of Logical Reasoning

et al. 2015

Self Cite

View full text Add to dashboard Cite

show abstract

“…Examples of computational semantic applications that include first‐order theorem provers are the implementation of the (negative parts of the) consistency and informativeness checks required by Van der Sandt's presupposition resolution algorithm (Blackburn et al. 2001), question interpretation in spoken dialogue systems (Bos and Gabsdil 2000), open‐domain question answering (Furbach et al. 2010) and recognising textual entailment (RTE; Akhmatova and Mollá 2006; Bos and Markert 2005).…”

Section: Inference Issuesmentioning

confidence: 99%

“…Such practical usages of theorem proving usually have a fall‐back strategy in place, particularly in open‐domain applications where finding proofs to a large extent depends on the background knowledge available. Furbach et al. (2010), in their application to question answering, use an algorithm that invokes relaxation of the query if no proof of the full query is found.…”

Section: Inference Issuesmentioning

confidence: 99%

A Survey of Computational Semantics: Representation, Inference and Knowledge in Wide‐Coverage Text Understanding

Bos

2011

Language and Linguist. Compass

View full text Add to dashboard Cite

The aim of computational semantics is to capture the meaning of natural language expressions in representations suitable for performing inferences, in the service of understanding human language in written or spoken form. First-order logic is a good starting point, both from the representation and inference point of view. But even if one makes the choice of first-order logic as representation language, this is not enough: the computational semanticist needs to make further decisions on how to model events, tense, modal contexts, anaphora and plural entities. Semantic representations are usually built on top of a syntactic analysis, using unification, techniques from the lambda-calculus or linear logic, to do the book-keeping of variable naming. Inference has many potential applications in computational semantics. One way to implement inference is using algorithms from automated deduction dedicated to first-order logic, such as theorem proving and model building. Theorem proving can help in finding contradictions or checking for new information. Finite model building can be seen as a complementary inference task to theorem proving, and it often makes sense to use both procedures in parallel. The models produced by model generators for texts not only show that the text is contradiction-free; they also can be used for disambiguation tasks and linking interpretation with the real world. To make interesting inferences, often additional background knowledge is required (not expressed in the analysed text or speech parts). This can be derived (and turned into first-order logic) from raw text, semistructured databases or large-scale lexical databases such as WordNet. Promising future research directions of computational semantics are investigating alternative representation and inference methods (using weaker variants of first-order logic, reasoning with defaults), and developing evaluation methods measuring the semantic adequacy of systems and formalisms.

show abstract

“…Question answering (QA) systems aim at providing concise answers to questions given a document collection. 1 The QA process is often divided into generation of answer candidates, using information retrieval techniques, followed by a validation and selection step that determines the final ranking. The quality of this ranking is crucial since users typically inspect only a few top-ranked results.…”

Section: Introductionmentioning

confidence: 99%

An Integrated Machine Learning and Case-Based Reasoning Approach to Answer Validation

Glöckner

Weis

2012

2012 11th International Conference on Machine Learning and Applications

View full text Add to dashboard Cite

We propose a case-based reasoning (CBR) approach to answer validation/answer scoring and reranking in question answering (QA) systems, where annotated answer candidates for known questions provide evidence for validating answer candidates for new questions. The use of CBR promises a continuous increase in answer quality, given user feedback that extends the case base. In the paper, we present the complete approach, emphasizing the use of CBR techniques, namely the structural case base, built with annotated MultiNet graphs, and corresponding graph similarity measures. We cover a priori relations to experienced answer candidates for former questions. We describe the adequate structuring of the case base and develop appropriate similarity measures. Finally we integrate CBR into an existing framework for answer validation and reranking that also includes logical answer validation and a shallow linguistic validation, using a learning-to-rank approach for the final answer ranking based on CBR-related features. In our experiments on QA@CLEF questions, the best learned models make heavy use of CBR features. The advantage already achieved by CBR will increase with time due to the automatic improvement with new user annotations given by relevance feedback.

show abstract

An application of automated reasoning in natural language question answering

Cited by 28 publications

References 35 publications

The RatioLog Project: Rational Extensions of Logical Reasoning

The RatioLog Project: Rational Extensions of Logical Reasoning

A Survey of Computational Semantics: Representation, Inference and Knowledge in Wide‐Coverage Text Understanding

An Integrated Machine Learning and Case-Based Reasoning Approach to Answer Validation

Contact Info

Product

Resources

About