An End-to-End Document-Level Neural Discourse Parser Exploiting Multi-Granularity Representations

12/21/2020
by   Ke Shi, et al.
0

Document-level discourse parsing, in accordance with the Rhetorical Structure Theory (RST), remains notoriously challenging. Challenges include the deep structure of document-level discourse trees, the requirement of subtle semantic judgments, and the lack of large-scale training corpora. To address such challenges, we propose to exploit robust representations derived from multiple levels of granularity across syntax and semantics, and in turn incorporate such representations in an end-to-end encoder-decoder neural architecture for more resourceful discourse processing. In particular, we first use a pre-trained contextual language model that embodies high-order and long-range dependency to enable finer-grain semantic, syntactic, and organizational representations. We further encode such representations with boundary and hierarchical information to obtain more refined modeling for document-level discourse processing. Experimental results show that our parser achieves the state-of-the-art performance, approaching human-level performance on the benchmarked RST dataset.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/28/2017

Joint Syntacto-Discourse Parsing and the Syntacto-Discourse Treebank

Discourse parsing has long been treated as a stand-alone problem indepen...
research
05/25/2017

Learning Structured Text Representations

In this paper, we focus on learning structure-aware document representat...
research
10/30/2019

Predicting Discourse Structure using Distant Supervision from Sentiment

Discourse parsing could not yet take full advantage of the neural NLP re...
research
02/03/2020

Learning Contextualized Document Representations for Healthcare Answer Retrieval

We present Contextual Discourse Vectors (CDV), a distributed document re...
research
05/23/2021

RST Parsing from Scratch

We introduce a novel top-down end-to-end formulation of document-level d...
research
04/14/2021

Predicting Discourse Trees from Transformer-based Neural Summarizers

Previous work indicates that discourse information benefits summarizatio...
research
10/21/2022

Modeling Document-level Temporal Structures for Building Temporal Dependency Graphs

We propose to leverage news discourse profiling to model document-level ...

Please sign up or login with your details

Forgot password? Click here to reset