• Computer Science
  • Published in HLT-NAACL 2013

Answer Extraction as Sequence Tagging with Tree Edit Distance

@inproceedings{Yao2013AnswerEA,
  title={Answer Extraction as Sequence Tagging with Tree Edit Distance},
  author={Xuchen Yao and Benjamin Van Durme and Chris Callison-Burch and Peter Clark},
  booktitle={HLT-NAACL},
  year={2013}
}
Our goal is to extract answers from preretrieved sentences for Question Answering (QA). We construct a linear-chain Conditional Random Field based on pairs of questions and their possible answer sentences, learning the association between questions and answer types. This casts answer extraction as an answer sequence tagging problem for the first time, where knowledge of shared structure between question and source sentence is incorporated through features based on Tree Edit Distance (TED). Our… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 143 CITATIONS

Computational Data and Social Networks

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Cross-Pair Text Representations for Answer Sentence Selection

VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Constrained Deep Answer Sentence Selection

VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Evidence Gathering and Language Alignment in Question Answering...

VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Improving Question Answering Sentence Selection by Rank Propagation

VIEW 6 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering

VIEW 4 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS
HIGHLY INFLUENCED

Modelling input texts: from Tree Kernels to Deep Learning

VIEW 9 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS
HIGHLY INFLUENCED

Back to Basics for Monolingual Alignment: Exploiting Word Similarity and Contextual Evidence

VIEW 18 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Automatic Feature Engineering for Answer Selection and Extraction

VIEW 14 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

Building structures from classifiers for passage reranking

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2012
2020

CITATION STATISTICS

  • 14 Highly Influenced Citations

  • Averaged 26 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 36 REFERENCES

TASM: Top-k Approximate Subtree Matching

VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL

What is the Jeopardy Model? A Quasi-Synchronous Grammar for QA

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Probabilistic treeedit models with structured latent variables for textual entailment and question answer

  • A Noah
  • 2010

Overview of the answer validation exercise 2008

  • Á. Rodrigo, A. Peñas, F. Verdejo.
  • Evaluating Systems for Multilingual and Multimodal Information Access, pages 296–313.
  • 2009
VIEW 2 EXCERPTS