Top-Down RST Parsing Utilizing Granularity Levels in Documents
Top-Down RST Parsing Utilizing Granularity Levels in Documents
复制标题
DOI：
10.1609/aaai.v34i05.6321
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Naoki Kobayashi;T. Hirao;Hidetaka Kamigaito;M. Okumura;M. Nagata
中科院分区：
文献类型：
--
作者：
Naoki Kobayashi;T. Hirao;Hidetaka Kamigaito;M. Okumura;M. Nagata
一些下游的NLP任务利用了从RST树转换而来的话语依存关系树。为了获得更好的话语依存关系树，我们需要提高RST树在结构上部的准确性。因此，我们提出了一种新的自顶向下的神经RST解析方法。然后，我们利用文档中的三个粒度，段落、句子和基本语篇单元(EDU)来准确高效地解析文档。对于每个粒度级别，通过递归地将较大的文本跨度拆分成两个较小的文本跨度，同时预测划分的跨度的核度和关系标签，以自上而下的方式完成解析。在RST-DT语料库上的实验结果表明，我们的方法达到了最新的结果，未标记的SPAN分数为87.0，有核标记的SPAN分数为74.6，与最新的60.0关系标记的SPAN分数的结果相当。此外，从我们的RST树转换而来的话语依存关系树也达到了最先进的结果，未标记依恋得分为64.9，标记依恋得分为48.5。
Some downstream NLP tasks exploit discourse dependency trees converted from RST trees. To obtain better discourse dependency trees, we need to improve the accuracy of RST trees at the upper parts of the structures. Thus, we propose a novel neural top-down RST parsing method. Then, we exploit three levels of granularity in a document, paragraphs, sentences and Elementary Discourse Units (EDUs), to parse a document accurately and efficiently. The parsing is done in a top-down manner for each granularity level, by recursively splitting a larger text span into two smaller ones while predicting nuclearity and relation labels for the divided spans. The results on the RST-DT corpus show that our method achieved the state-of-the-art results, 87.0 unlabeled span score, 74.6 nuclearity labeled span score, and the comparable result with the state-of-the-art, 60.0 relation labeled span score. Furthermore, discourse dependency trees converted from our RST trees also achieved the state-of-the-art results, 64.9 unlabeled attachment score and 48.5 labeled attachment score.