• Publications
  • Influence
A Macro Discourse Primary and Secondary Relation Recognition Method Based on Topic Similarity
蒋峰,褚晓敏,徐昇,李培峰,朱巧明 (苏州大学计算机科学与技术学院,江苏 苏州 215006; 江苏省计算机信息技术处理重点实验室,江苏 苏州 215006) 摘要:篇章分析是自然语言处理领域的一个重要任务。分析篇章主次关系有助于理解篇章的结构和语义, 并为自然语言处理的应用提供有力的支持。本文在微观篇章主次关系识别研究的基础上,重点研究宏观篇 章主次关系,提出了一种基于 word2vec 和Expand
  • 4
  • 3
  • PDF
MCDTB: A Macro-level Chinese Discourse TreeBank
TLDR
This paper uses the RST style to annotate macro discourse structure, nuclearity and relationship and constructs a Macro Chinese Discourse Treebank (MCDTB) including 720 articles. Expand
  • 7
  • 1
Topic Tensor Network for Implicit Discourse Relation Recognition in Chinese
TLDR
In this paper, we propose a topic tensor network to recognize Chinese implicit discourse relations with both sentence-level and topic-level representations. Expand
  • 6
  • PDF
Employing Text Matching Network to Recognise Nuclearity in Chinese Discourse
TLDR
We propose a novel text matching network (TMN) that encodes the discourse units and the paragraphs by combining Bi-LSTM and CNN to capture both global dependency information and local n-gram information. Expand
  • 4
Building a Macro Chinese Discourse Treebank
TLDR
Discourse structure analysis is an important research topic in natural language processing. Expand
  • 1
  • PDF