Repository logo
 

Event-Related Features in Feedforward Neural Networks Contribute to Identifying Causal Relations in Discourse

Accepted version
Peer-reviewed

Type

Conference Object

Change log

Authors

Ponti, EM 
Korhonen, A 

Abstract

Causal relations play a key role in information extraction and reasoning. Most of the times, their expression is ambiguous or implicit, i.e. without signals in the text. This makes their identification challenging. We aim to improve their identification by implementing a Feedforward Neural Network with a novel set of features for this task. In particular, these are based on the position of event mentions and the semantics of events and participants. The resulting classifier outperforms strong baselines on two datasets (the Penn Discourse Treebank and the CSTNews corpus) annotated with different schemes and containing examples in two languages, English and Portuguese. This result demonstrates the importance of events for identifying discourse relations.

Description

Keywords

Discourse Relations, NLP, Multi-Layer Perceptron, Event Semantics

Journal Title

LSDSem 2017 - 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics, Proceedings of the Workshop

Conference Name

EACL 2017

Journal ISSN

Volume Title

Publisher

Sponsorship
European Research Council (648909)