Quantitative evaluation of passage retrieval algorithms for question answering

Tellex, Stefanie; Katz, Boris; Lin, Jimmy; Fernandes, Aaron; Marton, Gregory

doi:10.1145/860442.860445

Cited by 62 publications

(71 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Typically, QA systems are organized in a pipelined structure, where the input to the system is a natural language question and the output is a ranked list of n answers. The importance of the retrieval component in a QA system has been highlighted in the field [2], [9], [10], [11]. If a bad set of passages is retrieved, not even containing a single answer to the posed question, the QA system fails at the retrieval step itself for that question.…”

Section: Related Workmentioning

confidence: 99%

“…Prior work in the area of factoid question answering (QA) showed that the passage retrieval phase is critical [2], [10], [11]: many of the retrieved passages are non-relevant because they do not contain a correct answer to the question despite the presence of common terms between the retrieved passages and the question. Therefore such passages must be eliminated post-retrieval.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Passage Reranking for Question Answering Using Syntactic Structures and Answer Types

Aktolga

Allan

Smith

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Passage Retrieval is a crucial step in question answering systems, one that has been well researched in the past. Due to the vocabulary mismatch problem and independence assumption of bag-of-words retrieval models, correct passages are often ranked lower than other incorrect passages in the retrieved list. Whereas in previous work, passages are reranked only on the basis of syntactic structures of questions and answers, our method achieves a better ranking by aligning the syntactic structures based on the question's answer type and detected named entities in the candidate passage. We compare our technique with strong retrieval and reranking baselines. Experimental results using the TREC QA 1999-2003 datasets show that our method significantly outperforms the baselines over all ranks in terms of the MRR measure.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Passage Reranking for Question Answering Using Syntactic Structures and Answer Types

Aktolga

Allan

Smith

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Vector representation of words are presently being used to solve a variety of problems like document classification (Sebastiani, 2002), question answering (Tellex et al, 2003) and chunking (Turian et al, 2010).…”

Section: Introductionmentioning

confidence: 99%

Exploiting Morphological Regularities in Distributional Word Representations

Akhtar

Vajpayee²,

Srivastava

et al. 2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

We present a simple, fast and unsupervised approach for exploiting morphological regularities present in high dimensional vector spaces. We propose a novel method for generating embeddings of words from their morphological variants using morphological transformation operators. We evaluate this approach on MSR word analogy test set (Mikolov et al., 2013d) with an accuracy of 85% which is 12% higher than the previous best known system.

show abstract

“…The representations can be used as basic features in a variety of applications, such as information retrieval (Manning et al, 2008), named entity recognition (Collobert et al, 2011), question answering (Tellex et al, 2003), disambiguation (Schütze, 1998), and parsing (Socher et al, 2011).…”

Section: Introductionmentioning

confidence: 99%

Learning Word Representations by Jointly Modeling Syntagmatic and Paradigmatic Relations

Sun¹,

Guo²,

Lan³

et al. 2015

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Confere

View full text Add to dashboard Cite

Vector space representation of words has been widely used to capture fine-grained linguistic regularities, and proven to be successful in various natural language processing tasks in recent years. However, existing models for learning word representations focus on either syntagmatic or paradigmatic relations alone. In this paper, we argue that it is beneficial to jointly modeling both relations so that we can not only encode different types of linguistic properties in a unified way, but also boost the representation learning due to the mutual enhancement between these two types of relations. We propose two novel distributional models for word representation using both syntagmatic and paradigmatic relations via a joint training objective. The proposed models are trained on a public Wikipedia corpus, and the learned representations are evaluated on word analogy and word similarity tasks. The results demonstrate that the proposed models can perform significantly better than all the state-of-the-art baseline methods on both tasks.

show abstract

Quantitative evaluation of passage retrieval algorithms for question answering

Cited by 62 publications

References 0 publications

Passage Reranking for Question Answering Using Syntactic Structures and Answer Types

Passage Reranking for Question Answering Using Syntactic Structures and Answer Types

Exploiting Morphological Regularities in Distributional Word Representations

Learning Word Representations by Jointly Modeling Syntagmatic and Paradigmatic Relations

Contact Info

Product

Resources

About