Sentence Pair Scoring: Towards Unified Framework for Text Comprehension

@article{Baudis2016SentencePS,
  title={Sentence Pair Scoring: Towards Unified Framework for Text Comprehension},
  author={Petr Baudis and Jan Sediv{\'y}},
  journal={CoRR},
  year={2016},
  volume={abs/1603.06127}
}
We review the task of Sentence Pair Scoring, popular in the literature in various forms — slanted as Answer Sentence Selection, Paraphrasing, Semantic Text Scoring, Next Utterance Ranking, Recognizing Textual Entailment or e.g. a component of Memory Networks. We argue that such tasks are similar from the model perspective (especially in the context of high-capacity deep neural models) and propose new baselines by comparing the performance of popular convolutional, recurrent and attentionbased… CONTINUE READING

Similar Papers

Loading similar papers…