paper-with-me

홈 › Papers

Predicting Discourse Trees from Transformer-based Neural Summarizers

2021-04-14 · NAACL 2021 4 · Wen Xiao, Patrick Huber, Giuseppe Carenini

Previous work indicates that discourse information benefits summarization. In this paper, we explore whether this synergy between discourse and summarization is bidirectional, by inferring document-level discourse trees from pre-trained neural summarizers. In particular, we generate unlabeled RST-style discourse trees from the self-attention matrices of the transformer model. Experiments across models and datasets reveal that the summarizer learns both, dependency- and constituency-style discourse information, which is typically encoded in a single head, covering long- and short-distance discourse dependencies. Overall, the experimental results suggest that the learned discourse information is general and transferable inter-domain.

📄 PDF Abstract BibTeX arXiv:2104.07058

Code (1)

Wendy-Xiao/summ_guided_disco_parser 공식 구현 pytorch

Tasks

Discourse Parsing

Similar Papers 제목 키워드 기반

Discourse-Aware Hierarchical Attention Network for Extractive Single-Document Summarization

2019-09-01 · RANLP 2019 9 · Tatsuya Ishigaki, Hidetaka Kamigaito, Hiroya Takamura, Manabu Okumura

Discourse relations between sentences are often represented as a tree, and the tree structure provides important information for summarizers to create a short and coherent summary. However, current neural network-based s…

Document SummarizationSentence

Top-Down RST Parsing Utilizing Granularity Levels in Documents

2020-04-03 · Naoki Kobayashi, Tsutomu Hirao, Hidetaka Kamigaito, Manabu Okumura 외

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,…

Discourse ParsingRelation

Evaluating Discourse in Structured Text Representations

2019-06-04 · ACL 2019 7 · Elisa Ferracane, Greg Durrett, Junyi Jessy Li, Katrin Erk

Discourse structure is integral to understanding a text and is helpful in many NLP tasks. Learning latent representations of discourse is an attractive alternative to acquiring expensive labeled discourse data. Liu and L…

text-classificationText Classification

Improve Discourse Dependency Parsing with Contextualized Representations

2022-05-04 · Findings (NAACL) 2022 7 · Yifei Zhou, Yansong Feng

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 meani…

ArticlesDependency Parsing

A Dependency Perspective on RST Discourse Parsing and Evaluation

2018-06-01 · CL 2018 6 · Mathieu Morey, Philippe Muller, Nicholas Asher

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