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.
@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}
}