@inproceedings{ouchi-etal-2017-neural,
title = "Neural Modeling of Multi-Predicate Interactions for {J}apanese Predicate Argument Structure Analysis",
author = "Ouchi, Hiroki and
Shindo, Hiroyuki and
Matsumoto, Yuji",
editor = "Barzilay, Regina and
Kan, Min-Yen",
booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P17-1146",
doi = "10.18653/v1/P17-1146",
pages = "1591--1600",
abstract = "The performance of Japanese predicate argument structure (PAS) analysis has improved in recent years thanks to the joint modeling of interactions between multiple predicates. However, this approach relies heavily on syntactic information predicted by parsers, and suffers from errorpropagation. To remedy this problem, we introduce a model that uses grid-type recurrent neural networks. The proposed model automatically induces features sensitive to multi-predicate interactions from the word sequence information of a sentence. Experiments on the NAIST Text Corpus demonstrate that without syntactic information, our model outperforms previous syntax-dependent models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ouchi-etal-2017-neural">
<titleInfo>
<title>Neural Modeling of Multi-Predicate Interactions for Japanese Predicate Argument Structure Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Ouchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroyuki</namePart>
<namePart type="family">Shindo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Barzilay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The performance of Japanese predicate argument structure (PAS) analysis has improved in recent years thanks to the joint modeling of interactions between multiple predicates. However, this approach relies heavily on syntactic information predicted by parsers, and suffers from errorpropagation. To remedy this problem, we introduce a model that uses grid-type recurrent neural networks. The proposed model automatically induces features sensitive to multi-predicate interactions from the word sequence information of a sentence. Experiments on the NAIST Text Corpus demonstrate that without syntactic information, our model outperforms previous syntax-dependent models.</abstract>
<identifier type="citekey">ouchi-etal-2017-neural</identifier>
<identifier type="doi">10.18653/v1/P17-1146</identifier>
<location>
<url>https://aclanthology.org/P17-1146</url>
</location>
<part>
<date>2017-07</date>
<extent unit="page">
<start>1591</start>
<end>1600</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Modeling of Multi-Predicate Interactions for Japanese Predicate Argument Structure Analysis
%A Ouchi, Hiroki
%A Shindo, Hiroyuki
%A Matsumoto, Yuji
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F ouchi-etal-2017-neural
%X The performance of Japanese predicate argument structure (PAS) analysis has improved in recent years thanks to the joint modeling of interactions between multiple predicates. However, this approach relies heavily on syntactic information predicted by parsers, and suffers from errorpropagation. To remedy this problem, we introduce a model that uses grid-type recurrent neural networks. The proposed model automatically induces features sensitive to multi-predicate interactions from the word sequence information of a sentence. Experiments on the NAIST Text Corpus demonstrate that without syntactic information, our model outperforms previous syntax-dependent models.
%R 10.18653/v1/P17-1146
%U https://aclanthology.org/P17-1146
%U https://doi.org/10.18653/v1/P17-1146
%P 1591-1600
Markdown (Informal)
[Neural Modeling of Multi-Predicate Interactions for Japanese Predicate Argument Structure Analysis](https://aclanthology.org/P17-1146) (Ouchi et al., ACL 2017)
ACL