@inproceedings{kurfali-ostling-2019-zero,
title = "Zero-shot transfer for implicit discourse relation classification",
author = {Kurfal{\i}, Murathan and
{\"O}stling, Robert},
booktitle = "Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue",
month = sep,
year = "2019",
address = "Stockholm, Sweden",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5927",
doi = "10.18653/v1/W19-5927",
pages = "226--231",
abstract = "Automatically classifying the relation between sentences in a discourse is a challenging task, in particular when there is no overt expression of the relation. It becomes even more challenging by the fact that annotated training data exists only for a small number of languages, such as English and Chinese. We present a new system using zero-shot transfer learning for implicit discourse relation classification, where the only resource used for the target language is unannotated parallel text. This system is evaluated on the discourse-annotated TED-MDB parallel corpus, where it obtains good results for all seven languages using only English training data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kurfali-ostling-2019-zero">
<titleInfo>
<title>Zero-shot transfer for implicit discourse relation classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Murathan</namePart>
<namePart type="family">Kurfalı</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Östling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-sep</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Stockholm, Sweden</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatically classifying the relation between sentences in a discourse is a challenging task, in particular when there is no overt expression of the relation. It becomes even more challenging by the fact that annotated training data exists only for a small number of languages, such as English and Chinese. We present a new system using zero-shot transfer learning for implicit discourse relation classification, where the only resource used for the target language is unannotated parallel text. This system is evaluated on the discourse-annotated TED-MDB parallel corpus, where it obtains good results for all seven languages using only English training data.</abstract>
<identifier type="citekey">kurfali-ostling-2019-zero</identifier>
<identifier type="doi">10.18653/v1/W19-5927</identifier>
<location>
<url>https://aclanthology.org/W19-5927</url>
</location>
<part>
<date>2019-sep</date>
<extent unit="page">
<start>226</start>
<end>231</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zero-shot transfer for implicit discourse relation classification
%A Kurfalı, Murathan
%A Östling, Robert
%S Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue
%D 2019
%8 sep
%I Association for Computational Linguistics
%C Stockholm, Sweden
%F kurfali-ostling-2019-zero
%X Automatically classifying the relation between sentences in a discourse is a challenging task, in particular when there is no overt expression of the relation. It becomes even more challenging by the fact that annotated training data exists only for a small number of languages, such as English and Chinese. We present a new system using zero-shot transfer learning for implicit discourse relation classification, where the only resource used for the target language is unannotated parallel text. This system is evaluated on the discourse-annotated TED-MDB parallel corpus, where it obtains good results for all seven languages using only English training data.
%R 10.18653/v1/W19-5927
%U https://aclanthology.org/W19-5927
%U https://doi.org/10.18653/v1/W19-5927
%P 226-231
Markdown (Informal)
[Zero-shot transfer for implicit discourse relation classification](https://aclanthology.org/W19-5927) (Kurfalı & Östling, 2019)
ACL