A PDTB-Styled End-to-End Discourse Parser

11/03/2010
by   Ziheng Lin, et al.
0

We have developed a full discourse parser in the Penn Discourse Treebank (PDTB) style. Our trained parser first identifies all discourse and non-discourse relations, locates and labels their arguments, and then classifies their relation types. When appropriate, the attribution spans to these relations are also determined. We present a comprehensive evaluation from both component-wise and error-cascading perspectives.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/31/2017

Shallow Discourse Parsing with Maximum Entropy Model

In recent years, more research has been devoted to studying the subtask ...
research
12/03/2016

Using Discourse Signals for Robust Instructor Intervention Prediction

We tackle the prediction of instructor intervention in student posts fro...
research
08/19/2017

The CLaC Discourse Parser at CoNLL-2015

This paper describes our submission (kosseim15) to the CoNLL-2015 shared...
research
04/01/2022

Revisiting Shallow Discourse Parsing in the PDTB-3: Handling Intra-sentential Implicits

In the PDTB-3, several thousand implicit discourse relations were newly ...
research
09/07/2017

Leveraging Discourse Information Effectively for Authorship Attribution

We explore techniques to maximize the effectiveness of discourse informa...
research
08/19/2017

Measuring the Effect of Discourse Relations on Blog Summarization

The work presented in this paper attempts to evaluate and quantify the u...
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...

Please sign up or login with your details

Forgot password? Click here to reset