BriefGPT.xyz
Oct, 2018
探索用于解析话语表示结构的神经方法
Exploring Neural Methods for Parsing Discourse Representation Structures
HTML
PDF
Rik van Noord, Lasha Abzianidze, Antonio Toral, Johan Bos
TL;DR
提出了一种基于Neural的序列到序列的语义解析器，它能够高准确率地产生英语句子的DRSs，并通过引入De Bruijn索引消除变量名以提高解析器性能，以及加入银标注数据来进一步提高性能。
Abstract
neural methods
have had several recent successes in
semantic parsing
, though they have yet to face the challenge of producing meaning representations based on formal semantics. We present a sequence-to-sequence n
→