Multi-level Head-wise Match and Aggregation in Transformer for Textual Sequence Matching
national conference on artificial intelligence, 2020.
摘要：
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 matchi...更多
代码：
数据：
下载 PDF 全文
标签
评论