English

Multi-level Head-wise Match and Aggregation in Transformer for Textual Sequence Matching

Computation and Language 2020-01-22 v1

Abstract

Transformer has been successfully applied to many natural language processing tasks. However, for textual sequence matching, simple matching between the representation of a pair of sequences might bring in unnecessary noise. In this paper, we propose a new approach to sequence pair matching with Transformer, by learning head-wise matching representations on multiple levels. Experiments show that our proposed approach can achieve new state-of-the-art performance on multiple tasks that rely only on pre-computed sequence-vector-representation, such as SNLI, MNLI-match, MNLI-mismatch, QQP, and SQuAD-binary.

Keywords

Cite

@article{arxiv.2001.07234,
  title  = {Multi-level Head-wise Match and Aggregation in Transformer for Textual Sequence Matching},
  author = {Shuohang Wang and Yunshi Lan and Yi Tay and Jing Jiang and Jingjing Liu},
  journal= {arXiv preprint arXiv:2001.07234},
  year   = {2020}
}

Comments

AAAI 2020, 8 pages

R2 v1 2026-06-23T13:15:52.866Z