@inproceedings{emelin-sennrich-2021-wino,
title = "Wino-{X}: Multilingual {W}inograd Schemas for Commonsense Reasoning and Coreference Resolution",
author = "Emelin, Denis and
Sennrich, Rico",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.670/",
doi = "10.18653/v1/2021.emnlp-main.670",
pages = "8517--8532",
abstract = "Winograd schemas are a well-established tool for evaluating coreference resolution (CoR) and commonsense reasoning (CSR) capabilities of computational models. So far, schemas remained largely confined to English, limiting their utility in multilingual settings. This work presents Wino-X, a parallel dataset of German, French, and Russian schemas, aligned with their English counterparts. We use this resource to investigate whether neural machine translation (NMT) models can perform CoR that requires commonsense knowledge and whether multilingual language models (MLLMs) are capable of CSR across multiple languages. Our findings show Wino-X to be exceptionally challenging for NMT systems that are prone to undesirable biases and unable to detect disambiguating information. We quantify biases using established statistical methods and define ways to address both of these issues. We furthermore present evidence of active cross-lingual knowledge transfer in MLLMs, whereby fine-tuning models on English schemas yields CSR improvements in other languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="emelin-sennrich-2021-wino">
<titleInfo>
<title>Wino-X: Multilingual Winograd Schemas for Commonsense Reasoning and Coreference Resolution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Denis</namePart>
<namePart type="family">Emelin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rico</namePart>
<namePart type="family">Sennrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Winograd schemas are a well-established tool for evaluating coreference resolution (CoR) and commonsense reasoning (CSR) capabilities of computational models. So far, schemas remained largely confined to English, limiting their utility in multilingual settings. This work presents Wino-X, a parallel dataset of German, French, and Russian schemas, aligned with their English counterparts. We use this resource to investigate whether neural machine translation (NMT) models can perform CoR that requires commonsense knowledge and whether multilingual language models (MLLMs) are capable of CSR across multiple languages. Our findings show Wino-X to be exceptionally challenging for NMT systems that are prone to undesirable biases and unable to detect disambiguating information. We quantify biases using established statistical methods and define ways to address both of these issues. We furthermore present evidence of active cross-lingual knowledge transfer in MLLMs, whereby fine-tuning models on English schemas yields CSR improvements in other languages.</abstract>
<identifier type="citekey">emelin-sennrich-2021-wino</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.670</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.670/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>8517</start>
<end>8532</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Wino-X: Multilingual Winograd Schemas for Commonsense Reasoning and Coreference Resolution
%A Emelin, Denis
%A Sennrich, Rico
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F emelin-sennrich-2021-wino
%X Winograd schemas are a well-established tool for evaluating coreference resolution (CoR) and commonsense reasoning (CSR) capabilities of computational models. So far, schemas remained largely confined to English, limiting their utility in multilingual settings. This work presents Wino-X, a parallel dataset of German, French, and Russian schemas, aligned with their English counterparts. We use this resource to investigate whether neural machine translation (NMT) models can perform CoR that requires commonsense knowledge and whether multilingual language models (MLLMs) are capable of CSR across multiple languages. Our findings show Wino-X to be exceptionally challenging for NMT systems that are prone to undesirable biases and unable to detect disambiguating information. We quantify biases using established statistical methods and define ways to address both of these issues. We furthermore present evidence of active cross-lingual knowledge transfer in MLLMs, whereby fine-tuning models on English schemas yields CSR improvements in other languages.
%R 10.18653/v1/2021.emnlp-main.670
%U https://aclanthology.org/2021.emnlp-main.670/
%U https://doi.org/10.18653/v1/2021.emnlp-main.670
%P 8517-8532
Markdown (Informal)
[Wino-X: Multilingual Winograd Schemas for Commonsense Reasoning and Coreference Resolution](https://aclanthology.org/2021.emnlp-main.670/) (Emelin & Sennrich, EMNLP 2021)
ACL