@inproceedings{garcia-ferrero-etal-2022-model,
title = "Model and Data Transfer for Cross-Lingual Sequence Labelling in Zero-Resource Settings",
author = "Garc{\'\i}a-Ferrero, Iker and
Agerri, Rodrigo and
Rigau, German",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.478",
doi = "10.18653/v1/2022.findings-emnlp.478",
pages = "6403--6416",
abstract = "Zero-resource cross-lingual transfer approaches aim to apply supervised modelsfrom a source language to unlabelled target languages. In this paper we performan in-depth study of the two main techniques employed so far for cross-lingualzero-resource sequence labelling, based either on data or model transfer. Although previous research has proposed translation and annotation projection(data-based cross-lingual transfer) as an effective technique for cross-lingualsequence labelling, in this paper we experimentally demonstrate that highcapacity multilingual language models applied in a zero-shot (model-basedcross-lingual transfer) setting consistently outperform data-basedcross-lingual transfer approaches. A detailed analysis of our results suggeststhat this might be due to important differences in language use. Morespecifically, machine translation often generates a textual signal which isdifferent to what the models are exposed to when using gold standard data,which affects both the fine-tuning and evaluation processes. Our results alsoindicate that data-based cross-lingual transfer approaches remain a competitiveoption when high-capacity multilingual language models are not available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garcia-ferrero-etal-2022-model">
<titleInfo>
<title>Model and Data Transfer for Cross-Lingual Sequence Labelling in Zero-Resource Settings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iker</namePart>
<namePart type="family">García-Ferrero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodrigo</namePart>
<namePart type="family">Agerri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Rigau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Zero-resource cross-lingual transfer approaches aim to apply supervised modelsfrom a source language to unlabelled target languages. In this paper we performan in-depth study of the two main techniques employed so far for cross-lingualzero-resource sequence labelling, based either on data or model transfer. Although previous research has proposed translation and annotation projection(data-based cross-lingual transfer) as an effective technique for cross-lingualsequence labelling, in this paper we experimentally demonstrate that highcapacity multilingual language models applied in a zero-shot (model-basedcross-lingual transfer) setting consistently outperform data-basedcross-lingual transfer approaches. A detailed analysis of our results suggeststhat this might be due to important differences in language use. Morespecifically, machine translation often generates a textual signal which isdifferent to what the models are exposed to when using gold standard data,which affects both the fine-tuning and evaluation processes. Our results alsoindicate that data-based cross-lingual transfer approaches remain a competitiveoption when high-capacity multilingual language models are not available.</abstract>
<identifier type="citekey">garcia-ferrero-etal-2022-model</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.478</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.478</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>6403</start>
<end>6416</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Model and Data Transfer for Cross-Lingual Sequence Labelling in Zero-Resource Settings
%A García-Ferrero, Iker
%A Agerri, Rodrigo
%A Rigau, German
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F garcia-ferrero-etal-2022-model
%X Zero-resource cross-lingual transfer approaches aim to apply supervised modelsfrom a source language to unlabelled target languages. In this paper we performan in-depth study of the two main techniques employed so far for cross-lingualzero-resource sequence labelling, based either on data or model transfer. Although previous research has proposed translation and annotation projection(data-based cross-lingual transfer) as an effective technique for cross-lingualsequence labelling, in this paper we experimentally demonstrate that highcapacity multilingual language models applied in a zero-shot (model-basedcross-lingual transfer) setting consistently outperform data-basedcross-lingual transfer approaches. A detailed analysis of our results suggeststhat this might be due to important differences in language use. Morespecifically, machine translation often generates a textual signal which isdifferent to what the models are exposed to when using gold standard data,which affects both the fine-tuning and evaluation processes. Our results alsoindicate that data-based cross-lingual transfer approaches remain a competitiveoption when high-capacity multilingual language models are not available.
%R 10.18653/v1/2022.findings-emnlp.478
%U https://aclanthology.org/2022.findings-emnlp.478
%U https://doi.org/10.18653/v1/2022.findings-emnlp.478
%P 6403-6416
Markdown (Informal)
[Model and Data Transfer for Cross-Lingual Sequence Labelling in Zero-Resource Settings](https://aclanthology.org/2022.findings-emnlp.478) (García-Ferrero et al., Findings 2022)
ACL