DeepAI AI Chat
Log In Sign Up

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

by   Zheng Zhao, et al.

In the PDTB-3, several thousand implicit discourse relations were newly annotated within individual sentences, adding to the over 15,000 implicit relations annotated across adjacent sentences in the PDTB-2. Given that the position of the arguments to these intra-sentential implicits is no longer as well-defined as with inter-sentential implicits, a discourse parser must identify both their location and their sense. That is the focus of the current work. The paper provides a comprehensive analysis of our results, showcasing model performance under different scenarios, pointing out limitations and noting future directions.


Extending Implicit Discourse Relation Recognition to the PDTB-3

The PDTB-3 contains many more Implicit discourse relations than the prev...

A PDTB-Styled End-to-End Discourse Parser

We have developed a full discourse parser in the Penn Discourse Treebank...

Shallow Discourse Parsing with Maximum Entropy Model

In recent years, more research has been devoted to studying the subtask ...

What's Hard in English RST Parsing? Predictive Models for Error Analysis

Despite recent advances in Natural Language Processing (NLP), hierarchic...

Great Service! Fine-grained Parsing of Implicit Arguments

Broad-coverage meaning representations in NLP mostly focus on explicitly...

A description of Turkish Discourse Bank 1.2 and an examination of common dependencies in Turkish discourse

We describe Turkish Discourse Bank 1.2, the latest version of a discours...

The CLaC Discourse Parser at CoNLL-2016

This paper describes our submission "CLaC" to the CoNLL-2016 shared task...