• Computer Science
  • Published in ACL 2013

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 Peter 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… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 16 CITATIONS

Dualized Topic-Preserving Pseudo Relevance Feedback for Question Answering

VIEW 2 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

A Joint Model for Answer Sentence Ranking and Answer Extraction

VIEW 11 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Discriminative Information Retrieval for Knowledge Discovery

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND

APIBot: Question answering bot for API documentation

  • Yuan Tian, Ferdian Thung, Abhishek Sharma, David Lo
  • Computer Science
  • 2017 32nd IEEE/ACM International Conference on Automated Software Engineering (ASE)
  • 2017

References

Publications referenced by this paper.
SHOWING 1-10 OF 26 REFERENCES

Learning to rank for robust question answering

VIEW 1 EXCERPT

Overview of NTCIR-8 ACLIA IR4QA

VIEW 2 EXCERPTS