Experiments with open-domain textual Question Answering

Harabagiu, Sanda M.; Paşca, Marius; Maiorano, Steven J.

doi:10.3115/990820.990863

Cited by 96 publications

(59 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Due to the empirical success of this conceptually simple strategy at the first few TREC evaluations, it evolved into the standard paradigm for factoid question answering; see Hirschman and Gaizauskas [2001] for an overview. Although researchers have since developed more advanced techniques such as abductive inferencing [Harabagiu et al 2000b], feedback loops [Moldovan et al 2002], and fuzzy matching of syntactic relations [Cui et al 2005], factoid question answering is still very much driven by information retrieval and named-entity recognition technologies and dependent on large ontologies.…”

Section: Development Of the Redundancy-based Approachmentioning

confidence: 99%

An exploration of the principles underlying redundancy-based factoid question answering

Lin

2007

ACM Trans. Inf. Syst.

View full text Add to dashboard Cite

The so-called "redundancy-based" approach to question answering represents a successful strategy for mining answers to factoid questions such as "Who shot Abraham Lincoln?" from the World Wide Web. Through contrastive and ablation experiments with Aranea, a system that has performed well in several TREC QA evaluations, this work examines the underlying assumptions and principles behind redundancy-based techniques. Specifically, we develop two theses: that stable characteristics of data redundancy allow factoid systems to rely on external "black box" components, and that despite embodying a data-driven approach, redundancy-based methods encode a substantial amount of knowledge in the form of heuristics. Overall, this work attempts to address the broader question of "what really matters" and to provide guidance for future researchers.

show abstract

Section: Development Of the Redundancy-based Approachmentioning

confidence: 99%

An exploration of the principles underlying redundancy-based factoid question answering

Lin

2007

ACM Trans. Inf. Syst.

View full text Add to dashboard Cite

show abstract

“…Question analysis in QA determines answer type corresponding to question type using named entities, answer type taxonomies, and ontologies such as WordNet in addition to question analysis in IR systems [7], [8], [9]. The number of answer types varies widely from single digits to a few thousands.…”

Section: Introductionmentioning

confidence: 99%

Concept-Based Question Analysis for an Efficient Document Ranking

Shin

Ahn

Seo

2007

Computational Science – ICCS 2007

View full text Add to dashboard Cite

Abstract. This paper describes a concept-based question analysis for an efficient document ranking. Our idea is that we can rank efficiently documents containing answers for questions when we use well-defined concepts because concepts occurred in questions of same answer type are similar. That is, we can retrieve more relevant documents if we know the syntactic and semantic role of each word or phrase in question. For each answer type, we define a concept rule which contains core concepts occurred in questions of that answer type. Concept-based question analysis is a process which tags concepts to morphological analysis result of a user's question, determines the answer type, and extracts untagged concepts from it using a matched concept rule. Empirical results show that our concept-based question analysis can rank documents more efficiently than any other conventional approach. Also, concept-based approach has additional merits that it is language universal model, and can be combined with arbitrary conventional approaches.

show abstract

“…Although early work in IR (Croft and Lewis, 1987;Smith et al, 1989) along these lines have not been successful, recent attempts in question answering (Harabagiu et al, 2000;Small et al, 2004;Demner-Fushman and Lin, 2007) have demonstrated the effectiveness of frame-based retrieval. Recent work on structured queries (Bilotti et al, 2007) lends additional support to the effectiveness of automatic facet analysis, since there is often a correspondence between query clauses and facets.…”

Section: Mediated Search As a Retrieval Modelmentioning

confidence: 99%

Toward automatic facet analysis and need negotiation

Lin

Abels

2008

ACM Trans. Inf. Syst.

View full text Add to dashboard Cite

This work explores the hypothesis that interactions between a trained human search intermediary and an information seeker can inform the design of interactive IR systems. We discuss results from a controlled Wizard-of-Oz case study, set in the context of the TREC 2005 HARD track evaluation, in which a trained intermediary executed an integrated search and interaction strategy based on conceptual facet analysis and informed by need negotiation techniques common in reference interviews. Having a human "in the loop" yielded large improvements over fully-automated systems as measured by standard ranked-retrieval metrics, demonstrating the value of mediated search. We present a detailed analysis of the intermediary's actions to gain a deeper understanding of what worked and why. One contribution is a taxonomy of clarification types informed both by empirical results and existing theories in library and information science. We discuss how these findings can guide the development of future systems. Overall, this work illustrates how studying humaninformation seeking processes can lead to better information retrieval applications.

show abstract

Experiments with open-domain textual Question Answering

Cited by 96 publications

References 4 publications

An exploration of the principles underlying redundancy-based factoid question answering

An exploration of the principles underlying redundancy-based factoid question answering

Concept-Based Question Analysis for an Efficient Document Ranking

Toward automatic facet analysis and need negotiation

Contact Info

Product

Resources

About