A Top-down Neural Architecture towards Text-level Parsing of Discourse Rhetorical Structure
A Top-down Neural Architecture towards Text-level Parsing of Discourse Rhetorical Structure
复制标题
DOI：
10.18653/v1/2020.acl-main.569
复制
发表时间：
2020-05
期刊：
影响因子：
--
通讯作者：
Longyin Zhang;Yu Xing;F. Kong;Peifeng Li;Guodong Zhou
中科院分区：
文献类型：
--
作者：
Longyin Zhang;Yu Xing;F. Kong;Peifeng Li;Guodong Zhou
语篇修辞结构的文本级句法分析在自然语言的深层理解和各种下游应用中具有重要意义，近年来受到越来越多的关注。然而，以往的文本级语篇分析研究都是采用自底向上的方法，这使得DRS的确定仅限于局部信息，不能充分利用语篇整体信息。在本文中，我们证明从计算和感知的角度来看，自顶向下的架构更适合于文本级DRS解析。在此基础上，我们提出了一个自顶向下的神经网络结构的文本级DRS解析。特别是，我们铸造的话语分析作为一个递归的分裂点排名任务，其中一个分裂点被分类到不同的水平，根据其排名和与之相关的基本话语单位（EDU）相应地安排。通过这种方式，我们可以通过具有内部堆栈的编码器-解码器将完整的DRS确定为分层树结构。在英文RST-DT语料库和中文CDTB语料库上的实验结果表明，本文提出的自顶向下方法对文本级DRS句法分析是有效的。
Due to its great importance in deep natural language understanding and various down-stream applications, text-level parsing of discourse rhetorical structure (DRS) has been drawing more and more attention in recent years. However, all the previous studies on text-level discourse parsing adopt bottom-up approaches, which much limit the DRS determination on local information and fail to well benefit from global information of the overall discourse. In this paper, we justify from both computational and perceptive points-of-view that the top-down architecture is more suitable for text-level DRS parsing. On the basis, we propose a top-down neural architecture toward text-level DRS parsing. In particular, we cast discourse parsing as a recursive split point ranking task, where a split point is classified to different levels according to its rank and the elementary discourse units (EDUs) associated with it are arranged accordingly. In this way, we can determine the complete DRS as a hierarchical tree structure via an encoder-decoder with an internal stack. Experimentation on both the English RST-DT corpus and the Chinese CDTB corpus shows the great effectiveness of our proposed top-down approach towards text-level DRS parsing.