Using coreference for question answering

Morton, Thomas

doi:10.3115/1608810.1608826

Cited by 32 publications

(20 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, we believe that the retrieval and summarization components can be improved by incorporating automatic relevance feedback (Buckley, 1995) and coreference resolution. Morton (1999), for example, shows that coreference resolution improves passage retrieval for their question-answering system. We also plan to reconsider paragraph-based summaries given their coverage on the test corpus.…”

Section: Related Work and Conclusionmentioning

confidence: 99%

Examining the role of statistical and linguistic knowledge sources in a general-knowledge question-answering system

Cardiel¹,

Ng²,

Pierce³

et al. 2000

Proceedings of the Sixth Conference on Applied Natural Language Processing -

View full text Add to dashboard Cite

We describe and evaluate an implemented system for general-knowledge question answering. The system combines techniques for standard ad-hoc information retrieval (IR), query-dependent text summarization, and shallow syntactic and semantic sentence analysis. In a series of experiments we examine the role of each statistical and linguistic knowledge source in the question-answering system. In contrast to previous results, we find first that statistical knowledge of word co-occurrences as computed by IR vector space methods can be used to quickly and accurately locate the relevant documents for each question. The use of query-dependent text summarization techniques, however, provides only small increases in performance and severely limits recall levels when inaccurate. Nevertheless, it is the text summarization component that allows subsequent linguistic filters to focus on relevant passages. We find that even very weak linguistic knowledge can offer substantial improvements over purely IRbased techniques for question answering, especially when smoothly integrated with statistical preferences computed by the IR subsystems.

show abstract

Section: Related Work and Conclusionmentioning

confidence: 99%

Examining the role of statistical and linguistic knowledge sources in a general-knowledge question-answering system

Cardiel¹,

Ng²,

Pierce³

et al. 2000

Proceedings of the Sixth Conference on Applied Natural Language Processing -

View full text Add to dashboard Cite

show abstract

“…The mere task of producing the same results as those produced by humans is difficult and largely unsolved. There is nonetheless a strong interest in automatically identifying coreference links as they are needed by information extraction to merge different pieces of information referring to the same entity (McCarthy and Lehnert, 1995), by text summarization to produce a coherent and fluent summary (Azzam et al, 1999;Steinberger et al, 2007), by question answering to disambiguate references along a document (Morton, 1999;Vicedo and Ferrández, 2006), and by machine translation to translate pronouns correctly. Recently, state-of-the-art coreference resolution systems have been helpful for sentiment analysis (Nicolov et al, 2008), textual entailment Abad et al, 2010), citation matching and databases (Wick et al, 2009), machine reading (Poon et al, 2010), for learning narrative schemas (Chambers and Jurafsky, 2008), and for recovering implicit arguments (Gerber and Chai, 2010;Ruppenhofer et al, 2010).…”

mentioning

confidence: 99%

Coreference resolution: an empirical study based on SemEval-2010 shared Task 1

Màrquez

Recasens

Sapena

2012

Lang Resources & Evaluation

View full text Add to dashboard Cite

This paper presents an empirical evaluation of coreference resolution that covers several interrelated dimensions. The main goal is to complete the comparative analysis from the SemEval-2010 task on Coreference Resolution in Multiple Languages. To do so, the study restricts the number of languages and systems involved, but extends and deepens the analysis of the system outputs, including a more qualitative discussion. The paper compares three automatic coreference resolution systems for three languages (English, Catalan and Spanish) in four evaluation settings, and using four evaluation measures. Given that our main goal is not to provide a comparison between resolution algorithms, these are merely used as tools to shed light on the different conditions under which coreference resolution is evaluated. Although the dimensions are strongly interdependent, making it very difficult to extract general principles, the study reveals a series of interesting issues in relation to coreference resolution: the portability of systems across languages, the influence of the type and quality of input annotations, and the behavior of the scoring measures.

show abstract

“…By building the coreference chains present in a text, we can identify all the information about one entity. From a computational perspective, the identification of coreference links is crucial for a number of applications such as information extraction, text summarization, question answering, and machine translation (McCarthy and Lehnert 1995;Steinberger et al 2007;Morton 1999). From a linguistic point of view, capturing the way a discourse entity is repeatedly referred to throughout a discourse makes it possible to obtain the different ways an entity can be linguistically expressed.…”

mentioning

confidence: 99%

AnCora-CO: Coreferentially annotated corpora for Spanish and Catalan

Recasens

Martí

2009

Lang Resources & Evaluation

View full text Add to dashboard Cite

This article describes the enrichment of the AnCora corpora of Spanish and Catalan (400 k each) with coreference links between pronouns (including elliptical subjects and clitics), full noun phrases (including proper nouns), and discourse segments. The coding scheme distinguishes between identity links, predicative relations, and discourse deixis. Inter-annotator agreement on the link types is 85-89% above chance, and we provide an analysis of the sources of disagreement. The resulting corpora make it possible to train and test learning-based algorithms for automatic coreference resolution, as well as to carry out bottom-up linguistic descriptions of coreference relations as they occur in real data.

show abstract

Using coreference for question answering

Cited by 32 publications

References 1 publication

Examining the role of statistical and linguistic knowledge sources in a general-knowledge question-answering system

Examining the role of statistical and linguistic knowledge sources in a general-knowledge question-answering system

Coreference resolution: an empirical study based on SemEval-2010 shared Task 1

AnCora-CO: Coreferentially annotated corpora for Spanish and Catalan

Contact Info

Product

Resources

About