@inproceedings{ponti-korhonen-2017-event,
title = "Event-Related Features in Feedforward Neural Networks Contribute to Identifying Causal Relations in Discourse",
author = "Ponti, Edoardo Maria and
Korhonen, Anna",
editor = "Roth, Michael and
Mostafazadeh, Nasrin and
Chambers, Nathanael and
Louis, Annie",
booktitle = "Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-0903",
doi = "10.18653/v1/W17-0903",
pages = "25--30",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ponti-korhonen-2017-event">
<titleInfo>
<title>Event-Related Features in Feedforward Neural Networks Contribute to Identifying Causal Relations in Discourse</title>
</titleInfo>
<name type="personal">
<namePart type="given">Edoardo</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Ponti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Roth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nasrin</namePart>
<namePart type="family">Mostafazadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathanael</namePart>
<namePart type="family">Chambers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annie</namePart>
<namePart type="family">Louis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">ponti-korhonen-2017-event</identifier>
<identifier type="doi">10.18653/v1/W17-0903</identifier>
<location>
<url>https://aclanthology.org/W17-0903</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>25</start>
<end>30</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Event-Related Features in Feedforward Neural Networks Contribute to Identifying Causal Relations in Discourse
%A Ponti, Edoardo Maria
%A Korhonen, Anna
%Y Roth, Michael
%Y Mostafazadeh, Nasrin
%Y Chambers, Nathanael
%Y Louis, Annie
%S Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F ponti-korhonen-2017-event
%X 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.
%R 10.18653/v1/W17-0903
%U https://aclanthology.org/W17-0903
%U https://doi.org/10.18653/v1/W17-0903
%P 25-30
Markdown (Informal)
[Event-Related Features in Feedforward Neural Networks Contribute to Identifying Causal Relations in Discourse](https://aclanthology.org/W17-0903) (Ponti & Korhonen, LSDSem 2017)
ACL