Higher-order Lexical Semantic Models for Non-factoid Answer Reranking

@article{Fried2015HigherorderLS,
  title={Higher-order Lexical Semantic Models for Non-factoid Answer Reranking},
  author={Daniel Fried and Paul Edward Jansen and Gustave Hahn-Powell and Mihai Surdeanu and Peter Clark},
  journal={Transactions of the Association for Computational Linguistics},
  year={2015},
  volume={3},
  pages={197-210}
}
Lexical semantic models provide robust performance for question answering, but, in general, can only capitalize on direct evidence seen during training. For example, monolingual alignment models acquire term alignment probabilities from semi-structured data such as question-answer pairs; neural network language models learn term embeddings from unstructured text. All this knowledge is then used to estimate the semantic similarity between question and answer candidates. We introduce a higher… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 25 CITATIONS

Computational Natural Language Inference: Robust and Interpretable Question Answering

VIEW 15 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Framing QA as Building and Ranking Intersentence Answer Justifications

VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 39 REFERENCES

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

VIEW 2 EXCERPTS