Passage Reranking for Question Answering Using Syntactic Structures and Answer Types

Aktolga, Elif; Allan, James; Smith, David A.

doi:10.1007/978-3-642-20161-5_62

Cited by 22 publications

(21 citation statements)

References 7 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, PDQ's MAP performance is .31, .24, .21, and .18 for TREC'99, TREC'00, TREC'01, and TREC'02, respectively, while that of PDQ∧NEQ is .33, .26, .23, and .21. This finding, which echoes those from work on using named entities for improving passage retrieval performance for QA [3,5,1], attests to the effectiveness, in terms of retrieval performance, of our entity-based judge.…”

Section: Resultssupporting

confidence: 87%

See 1 more Smart Citation

Predicting the performance of passage retrieval for question answering

Krikon

Carmel

Kurland

2012

Proceedings of the 21st ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

We present a novel approach to predicting the performance of passage retrieval for question answering. That is, estimating the effectiveness, for answer extraction, of a list of passages retrieved in response to a question when relevance judgments are not available. Our prediction model integrates two types of estimates. The first estimates the probability that the information need expressed by the question is satisfied by the passages. This estimate is devised by adapting query-performance predictors developed for the document retrieval task. The second type estimates the probability that the passages contain the answers. This estimate relies on the occurrences of named entities that are likely to answer the question. Empirical evaluation demonstrates the merits of our prediction approach. For example, the prediction quality is much better than that of the only previous prediction method devised for the task at hand.

show abstract

Section: Resultssupporting

confidence: 87%

“…There is much work on using named entities for improving the passage retrieval performance for QA [10,3,8,1]. As noted above, our entity-based estimate is effective for both prediction and retrieval.…”

Section: Related Workmentioning

confidence: 89%

Predicting the performance of passage retrieval for question answering

Krikon

Carmel

Kurland

2012

Proceedings of the 21st ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

show abstract

“…In this perspective, a typical approach is to use subject-verb-object relations, e.g., as in [5]. Unfortunately, the large variability of natural language makes such triples rather sparse thus different methods explore soft matching (i.e., lexical similarity) based on answer types and named entity types, e.g., see [3]. Passage reranking using classifiers of question and answer pairs were proposed in [36,19].…”

Section: Related Workmentioning

confidence: 99%

Building structures from classifiers for passage reranking

Severyn

Nicosia

Moschitti

2013

Proceedings of the 22nd ACM International Conference on Conference on Information &Amp; Knowledge Management - CIKM '13

View full text Add to dashboard Cite

This paper shows that learning to rank models can be applied to automatically learn complex patterns, such as relational semantic structures occurring in questions and their answer passages. This is achieved by providing the learning algorithm with a tree representation derived from the syntactic trees of questions and passages connected by relational tags, where the latter are again provided by the means of automatic classifiers, i.e., question and focus classifiers and Named Entity Recognizers. This way effective structural relational patterns are implicitly encoded in the representation and can be automatically utilized by powerful machine learning models such as kernel methods.We conduct an extensive experimental evaluation of our models on well-known benchmarks from the question answer (QA) track of TREC challenges. The comparison with stateof-the-art systems and BM25 show a relative improvement in MAP of more than 14% and 45%, respectively. Further comparison on the task restricted to the answer sentence reranking shows an improvement in MAP of more than 8% over the state of the art.

show abstract

“…More traditional studies on passage reranking, exploiting structural information, were carried out in (Katz and Lin, 2003), whereas other methods explored soft matching (i.e., lexical similarity) based on answer and named entity types (Aktolga et al, 2011). (Radlinski and Joachims, 2006;Jeon et al, 2005) applied question and answer classifiers for passage reranking.…”

Section: Related Workmentioning

confidence: 99%

Learning to Rank Answer Candidates for Automatic Resolution of Crossword Puzzles

Barlacchi¹,

Nicosia²,

Moschitti³

2014

Proceedings of the Eighteenth Conference on Computational Natural Language Learning

View full text Add to dashboard Cite

In this paper, we study the impact of relational and syntactic representations for an interesting and challenging task: the automatic resolution of crossword puzzles. Automatic solvers are typically based on two answer retrieval modules: (i) a web search engine, e.g., Google, Bing, etc. and (ii) a database (DB) system for accessing previously resolved crossword puzzles. We show that learning to rank models based on relational syntactic structures defined between the clues and the answer can improve both modules above. In particular, our approach accesses the DB using a search engine and reranks its output by modeling paraphrasing. This improves on the MRR of previous system up to 53% in ranking answer candidates and greatly impacts on the resolution accuracy of crossword puzzles up to 15%.

show abstract

Passage Reranking for Question Answering Using Syntactic Structures and Answer Types

Cited by 22 publications

References 7 publications

Predicting the performance of passage retrieval for question answering

Predicting the performance of passage retrieval for question answering

Building structures from classifiers for passage reranking

Learning to Rank Answer Candidates for Automatic Resolution of Crossword Puzzles

Contact Info

Product

Resources

About