@inproceedings{kobayashi-etal-2019-split,
title = "Split or Merge: Which is Better for Unsupervised {RST} Parsing?",
author = "Kobayashi, Naoki and
Hirao, Tsutomu and
Nakamura, Kengo and
Kamigaito, Hidetaka and
Okumura, Manabu and
Nagata, Masaaki",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
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/D19-1587",
doi = "10.18653/v1/D19-1587",
pages = "5797--5802",
abstract = "Rhetorical Structure Theory (RST) parsing is crucial for many downstream NLP tasks that require a discourse structure for a text. Most of the previous RST parsers have been based on supervised learning approaches. That is, they require an annotated corpus of sufficient size and quality, and heavily rely on the language and domain dependent corpus. In this paper, we present two language-independent unsupervised RST parsing methods based on dynamic programming. The first one builds the optimal tree in terms of a dissimilarity score function that is defined for splitting a text span into smaller ones. The second builds the optimal tree in terms of a similarity score function that is defined for merging two adjacent spans into a large one. Experimental results on English and German RST treebanks showed that our parser based on span merging achieved the best score, around 0.8 F$_1$ score, which is close to the scores of the previous supervised parsers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kobayashi-etal-2019-split">
<titleInfo>
<title>Split or Merge: Which is Better for Unsupervised RST Parsing?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Naoki</namePart>
<namePart type="family">Kobayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsutomu</namePart>
<namePart type="family">Hirao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kengo</namePart>
<namePart type="family">Nakamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hidetaka</namePart>
<namePart type="family">Kamigaito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manabu</namePart>
<namePart type="family">Okumura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaaki</namePart>
<namePart type="family">Nagata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</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>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>Rhetorical Structure Theory (RST) parsing is crucial for many downstream NLP tasks that require a discourse structure for a text. Most of the previous RST parsers have been based on supervised learning approaches. That is, they require an annotated corpus of sufficient size and quality, and heavily rely on the language and domain dependent corpus. In this paper, we present two language-independent unsupervised RST parsing methods based on dynamic programming. The first one builds the optimal tree in terms of a dissimilarity score function that is defined for splitting a text span into smaller ones. The second builds the optimal tree in terms of a similarity score function that is defined for merging two adjacent spans into a large one. Experimental results on English and German RST treebanks showed that our parser based on span merging achieved the best score, around 0.8 F₁ score, which is close to the scores of the previous supervised parsers.</abstract>
<identifier type="citekey">kobayashi-etal-2019-split</identifier>
<identifier type="doi">10.18653/v1/D19-1587</identifier>
<location>
<url>https://aclanthology.org/D19-1587</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>5797</start>
<end>5802</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Split or Merge: Which is Better for Unsupervised RST Parsing?
%A Kobayashi, Naoki
%A Hirao, Tsutomu
%A Nakamura, Kengo
%A Kamigaito, Hidetaka
%A Okumura, Manabu
%A Nagata, Masaaki
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%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 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F kobayashi-etal-2019-split
%X Rhetorical Structure Theory (RST) parsing is crucial for many downstream NLP tasks that require a discourse structure for a text. Most of the previous RST parsers have been based on supervised learning approaches. That is, they require an annotated corpus of sufficient size and quality, and heavily rely on the language and domain dependent corpus. In this paper, we present two language-independent unsupervised RST parsing methods based on dynamic programming. The first one builds the optimal tree in terms of a dissimilarity score function that is defined for splitting a text span into smaller ones. The second builds the optimal tree in terms of a similarity score function that is defined for merging two adjacent spans into a large one. Experimental results on English and German RST treebanks showed that our parser based on span merging achieved the best score, around 0.8 F₁ score, which is close to the scores of the previous supervised parsers.
%R 10.18653/v1/D19-1587
%U https://aclanthology.org/D19-1587
%U https://doi.org/10.18653/v1/D19-1587
%P 5797-5802
Markdown (Informal)
[Split or Merge: Which is Better for Unsupervised RST Parsing?](https://aclanthology.org/D19-1587) (Kobayashi et al., EMNLP-IJCNLP 2019)
ACL
- Naoki Kobayashi, Tsutomu Hirao, Kengo Nakamura, Hidetaka Kamigaito, Manabu Okumura, and Masaaki Nagata. 2019. Split or Merge: Which is Better for Unsupervised RST Parsing?. 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 5797–5802, Hong Kong, China. Association for Computational Linguistics.