• Computer Science
  • Published in EMNLP 2013

Automatic Feature Engineering for Answer Selection and Extraction

@inproceedings{Severyn2013AutomaticFE,
  title={Automatic Feature Engineering for Answer Selection and Extraction},
  author={Aliaksei Severyn and Alessandro Moschitti},
  booktitle={EMNLP},
  year={2013}
}
This paper proposes a framework for automatically engineering features for two important tasks of question answering: answer sentence selection and answer extraction. We represent question and answer sentence pairs with linguistic structures enriched by semantic information, where the latter is produced by automatic classifiers, e.g., question classifier and Named Entity Recognizer. Tree kernels applied to such structures enable a simple way to generate highly discriminative structural features… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 86 CITATIONS

Attention-based neural network for short-text question answering

  • ICDLT '18
  • 2018
VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Answer Extraction with Multiple Extraction Engines for Web-Based Question Answering

VIEW 11 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

A Joint Model for Answer Sentence Ranking and Answer Extraction

  • Transactions of the Association for Computational Linguistics
  • 2016
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2014
2019

CITATION STATISTICS

  • 5 Highly Influenced Citations

  • Averaged 15 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 24 REFERENCES

What is the jeopardy model? a quasisynchronous grammar for qa

Mengqiu Wang, Noah A. Smith, Teruko Mitaura.
  • EMNLP.
  • 2007
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL