Improve Discourse Dependency Parsing with Contextualized Representations
Recent works show that discourse analysis benefits from modeling intra- and inter-sentential levels separately, where proper representations for text units of different granularities are desired to capture both the meaning of text units and their relations to the context. In this paper, we propose to take advantage of transformers to encode contextualized representations of units of different levels to dynamically capture the information required for discourse dependency analysis on intra- and inter-sentential levels. Motivated by the observation of writing patterns commonly shared across articles, we propose a novel method that treats discourse relation identification as a sequence labelling task, which takes advantage of structural information from the context of extracted discourse trees, and substantially outperforms traditional direct-classification methods. Experiments show that our model achieves state-of-the-art results on both English and Chinese datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
ArticlesDependency ParsingSimilar Papers 제목 키워드 기반
Improve Discourse Dependency Parsing with Contextualized Representations
Previous works show that discourse analysis benefits from modeling intra- and inter-sentential levels separately, where proper representations for text units of different granularities are desired to capture both the in…
ArticlesDependency ParsingExploring Contextualized Neural Language Models for Temporal Dependency Parsing
Extracting temporal relations between events and time expressions has many applications such as constructing event timelines and time-related question answering. It is a challenging problem which requires syntactic and s…
Dependency ParsingQuestion AnsweringSentenceSemi-supervised Domain Adaptation for Dependency Parsing via Improved Contextualized Word Representations
In recent years, parsing performance is dramatically improved on in-domain texts thanks to the rapid progress of deep neural network models. The major challenge for current parsing research is to improve parsing performa…
Dependency ParsingDomain AdaptationLanguage ModellingSemi-supervised Domain AdaptationAdapting Unsupervised Syntactic Parsing Methodology for Discourse Dependency Parsing
One of the main bottlenecks in developing discourse dependency parsers is the lack of annotated training data. A potential solution is to utilize abundant unlabeled data by using unsupervised techniques, but there is so …
Dependency ParsingDiscourse ParsingA Dependency Perspective on RST Discourse Parsing and Evaluation
Computational text-level discourse analysis mostly happens within Rhetorical Structure Theory (RST), whose structures have classically been presented as constituency trees, and relies on data from the RST Discourse Treeb…
Constituency ParsingDependency ParsingDiscourse Parsing