Corpus ID: 13508168

Automatic Coupling of Answer Extraction and Information Retrieval

@inproceedings{Yao2013AutomaticCO,
  title={Automatic Coupling of Answer Extraction and Information Retrieval},
  author={Xuchen Yao and Benjamin Van Durme and P. Clark},
  booktitle={ACL},
  year={2013}
}
Information Retrieval (IR) and Answer Extraction are often designed as isolated or loosely connected components in Question Answering (QA), with repeated overengineering on IR, and not necessarily performance gain for QA. We propose to tightly integrate them by coupling automatically learned features for answer extraction to a shallow-structured IR model. Our method is very quick to implement, and significantly improves IR for QA (measured in Mean Average Precision and Mean Reciprocal Rank) by… Expand
22 Citations
Discriminative Information Retrieval for Knowledge Discovery
  • PDF
Indirect Supervision for Relation Extraction using Question-Answer Pairs
  • 5
  • PDF
A Joint Model for Answer Sentence Ranking and Answer Extraction
  • 9
  • Highly Influenced
  • PDF
Discriminative Information Retrieval for Question Answering Sentence Selection
  • 15
  • PDF
Dualized Topic-Preserving Pseudo Relevance Feedback for Question Answering
  • Highly Influenced
Complementing Lexical Retrieval with Semantic Residual Embedding
  • 15
  • PDF
...
1
2
3
...

References

SHOWING 1-10 OF 28 REFERENCES
Structured retrieval for question answering
  • 100
  • PDF
Answer Sentence Retrieval by Matching Dependency Paths acquired from Question/Answer Sentence Pairs
  • 9
  • PDF
Answer Extraction as Sequence Tagging with Tree Edit Distance
  • 188
  • PDF
Question answering passage retrieval using dependency relations
  • 242
  • PDF
Rank learning for factoid question answering with linguistic and semantic constraints
  • 53
  • PDF
Using Semantic Roles to Improve Question Answering
  • 392
  • PDF
Question-answering by predictive annotation
  • 253
  • PDF
Answer typing for information retrieval
  • 3
  • PDF
...
1
2
3
...