Paraphrase-Driven Learning for Open Question Answering

@inproceedings{Fader2013ParaphraseDrivenLF,
  title={Paraphrase-Driven Learning for Open Question Answering},
  author={Anthony Fader and Luke S. Zettlemoyer and Oren Etzioni},
  booktitle={ACL},
  year={2013}
}
We study question answering as a machine learning problem, and induce a function that maps open-domain questions to queries over a database of web extractions. Given a large, community-authored, question-paraphrase corpus, we demonstrate that it is possible to learn a semantic lexicon and linear ranking function without manually annotating questions. Our approach automatically generalizes a seed lexicon and includes a scalable, parallelized perceptron parameter estimation scheme. Experiments… CONTINUE READING

Similar Papers

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • Experiments show that our approach more than quadruples the recall of the seed lexicon, with only an 8% loss in precision.
  • On known-answerable questions, the approach achieved 42% recall, with 77% precision, more than quadrupling the recall over a baseline system.

Citations

Publications citing this paper.
SHOWING 1-10 OF 174 CITATIONS

Character-Level Question Answering with Attention

VIEW 15 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Open Question Answering with Weakly Supervised Embedding Models

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Explorer Learning Embeddings to lexicalise RDF Properties

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2012
2019

CITATION STATISTICS

  • 38 Highly Influenced Citations

  • Averaged 27 Citations per year from 2017 through 2019