Abstract
High-level semantics tasks, e.g., paraphrasing, textual entailment or question answering, involve modeling of text pairs. Before the emergence of neural networks, this has been mostly performed using intra-pair features, which incorporate similarity scores or rewrite rules computed between the members within the same pair. In this paper, we compute scalar products between vectors representing similarity between members of different pairs, in place of simply using a single vector for each pair. This allows us to obtain a representation specific to any pair of pairs, which delivers the state of the art in answer sentence selection. Most importantly, our approach can outperform much more complex algorithms based on neural networks.- Anthology ID:
- D18-1240
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2162–2173
- Language:
- URL:
- https://aclanthology.org/D18-1240
- DOI:
- 10.18653/v1/D18-1240
- Cite (ACL):
- Kateryna Tymoshenko and Alessandro Moschitti. 2018. Cross-Pair Text Representations for Answer Sentence Selection. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2162–2173, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Cross-Pair Text Representations for Answer Sentence Selection (Tymoshenko & Moschitti, EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/D18-1240.pdf
- Code
- iKernels/RelTextRank
- Data
- WikiQA