@inproceedings{ringel-etal-2019-cross,
title = "Cross-Cultural Transfer Learning for Text Classification",
author = "Ringel, Dor and
Lavee, Gal and
Guy, Ido and
Radinsky, Kira",
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/D19-1400",
doi = "10.18653/v1/D19-1400",
pages = "3873--3883",
abstract = "Large training datasets are required to achieve competitive performance in most natural language tasks. The acquisition process for these datasets is labor intensive, expensive, and time consuming. This process is also prone to human errors. In this work, we show that cross-cultural differences can be harnessed for natural language text classification. We present a transfer-learning framework that leverages widely-available unaligned bilingual corpora for classification tasks, using no task-specific data. Our empirical evaluation on two tasks {--} formality classification and sarcasm detection {--} shows that the cross-cultural difference between German and American English, as manifested in product review text, can be applied to achieve good performance for formality classification, while the difference between Japanese and American English can be applied to achieve good performance for sarcasm detection {--} both without any task-specific labeled data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ringel-etal-2019-cross">
<titleInfo>
<title>Cross-Cultural Transfer Learning for Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dor</namePart>
<namePart type="family">Ringel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gal</namePart>
<namePart type="family">Lavee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ido</namePart>
<namePart type="family">Guy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kira</namePart>
<namePart type="family">Radinsky</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>Large training datasets are required to achieve competitive performance in most natural language tasks. The acquisition process for these datasets is labor intensive, expensive, and time consuming. This process is also prone to human errors. In this work, we show that cross-cultural differences can be harnessed for natural language text classification. We present a transfer-learning framework that leverages widely-available unaligned bilingual corpora for classification tasks, using no task-specific data. Our empirical evaluation on two tasks – formality classification and sarcasm detection – shows that the cross-cultural difference between German and American English, as manifested in product review text, can be applied to achieve good performance for formality classification, while the difference between Japanese and American English can be applied to achieve good performance for sarcasm detection – both without any task-specific labeled data.</abstract>
<identifier type="citekey">ringel-etal-2019-cross</identifier>
<identifier type="doi">10.18653/v1/D19-1400</identifier>
<location>
<url>https://aclanthology.org/D19-1400</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>3873</start>
<end>3883</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Cultural Transfer Learning for Text Classification
%A Ringel, Dor
%A Lavee, Gal
%A Guy, Ido
%A Radinsky, Kira
%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 ringel-etal-2019-cross
%X Large training datasets are required to achieve competitive performance in most natural language tasks. The acquisition process for these datasets is labor intensive, expensive, and time consuming. This process is also prone to human errors. In this work, we show that cross-cultural differences can be harnessed for natural language text classification. We present a transfer-learning framework that leverages widely-available unaligned bilingual corpora for classification tasks, using no task-specific data. Our empirical evaluation on two tasks – formality classification and sarcasm detection – shows that the cross-cultural difference between German and American English, as manifested in product review text, can be applied to achieve good performance for formality classification, while the difference between Japanese and American English can be applied to achieve good performance for sarcasm detection – both without any task-specific labeled data.
%R 10.18653/v1/D19-1400
%U https://aclanthology.org/D19-1400
%U https://doi.org/10.18653/v1/D19-1400
%P 3873-3883
Markdown (Informal)
[Cross-Cultural Transfer Learning for Text Classification](https://aclanthology.org/D19-1400) (Ringel et al., EMNLP-IJCNLP 2019)
ACL
- Dor Ringel, Gal Lavee, Ido Guy, and Kira Radinsky. 2019. Cross-Cultural Transfer Learning for Text Classification. 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 3873–3883, Hong Kong, China. Association for Computational Linguistics.