@inproceedings{moon-etal-2019-unified,
title = "A Unified Neural Coherence Model",
author = "Moon, Han Cheol and
Mohiuddin, Tasnim and
Joty, Shafiq and
Xu, Chi",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1231",
doi = "10.18653/v1/D19-1231",
pages = "2262--2272",
abstract = "Recently, neural approaches to coherence modeling have achieved state-of-the-art results in several evaluation tasks. However, we show that most of these models often fail on harder tasks with more realistic application scenarios. In particular, the existing models underperform on tasks that require the model to be sensitive to local contexts such as candidate ranking in conversational dialogue and in machine translation. In this paper, we propose a unified coherence model that incorporates sentence grammar, inter-sentence coherence relations, and global coherence patterns into a common neural framework. With extensive experiments on local and global discrimination tasks, we demonstrate that our proposed model outperforms existing models by a good margin, and establish a new state-of-the-art.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moon-etal-2019-unified">
<titleInfo>
<title>A Unified Neural Coherence Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="given">Cheol</namePart>
<namePart type="family">Moon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tasnim</namePart>
<namePart type="family">Mohiuddin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chi</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, neural approaches to coherence modeling have achieved state-of-the-art results in several evaluation tasks. However, we show that most of these models often fail on harder tasks with more realistic application scenarios. In particular, the existing models underperform on tasks that require the model to be sensitive to local contexts such as candidate ranking in conversational dialogue and in machine translation. In this paper, we propose a unified coherence model that incorporates sentence grammar, inter-sentence coherence relations, and global coherence patterns into a common neural framework. With extensive experiments on local and global discrimination tasks, we demonstrate that our proposed model outperforms existing models by a good margin, and establish a new state-of-the-art.</abstract>
<identifier type="citekey">moon-etal-2019-unified</identifier>
<identifier type="doi">10.18653/v1/D19-1231</identifier>
<location>
<url>https://aclanthology.org/D19-1231</url>
</location>
<part>
<date>2019-nov</date>
<extent unit="page">
<start>2262</start>
<end>2272</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Unified Neural Coherence Model
%A Moon, Han Cheol
%A Mohiuddin, Tasnim
%A Joty, Shafiq
%A Xu, Chi
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 nov
%I Association for Computational Linguistics
%C Hong Kong, China
%F moon-etal-2019-unified
%X Recently, neural approaches to coherence modeling have achieved state-of-the-art results in several evaluation tasks. However, we show that most of these models often fail on harder tasks with more realistic application scenarios. In particular, the existing models underperform on tasks that require the model to be sensitive to local contexts such as candidate ranking in conversational dialogue and in machine translation. In this paper, we propose a unified coherence model that incorporates sentence grammar, inter-sentence coherence relations, and global coherence patterns into a common neural framework. With extensive experiments on local and global discrimination tasks, we demonstrate that our proposed model outperforms existing models by a good margin, and establish a new state-of-the-art.
%R 10.18653/v1/D19-1231
%U https://aclanthology.org/D19-1231
%U https://doi.org/10.18653/v1/D19-1231
%P 2262-2272
Markdown (Informal)
[A Unified Neural Coherence Model](https://aclanthology.org/D19-1231) (Moon et al., EMNLP 2019)
ACL
- Han Cheol Moon, Tasnim Mohiuddin, Shafiq Joty, and Chi Xu. 2019. A Unified Neural Coherence Model. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2262–2272, Hong Kong, China. Association for Computational Linguistics.