@inproceedings{schmidt-etal-2022-slicer,
title = "{SLICER}: Sliced Fine-Tuning for Low-Resource Cross-Lingual Transfer for Named Entity Recognition",
author = "Schmidt, Fabian David and
Vuli{\'c}, Ivan and
Glava{\v{s}}, Goran",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.740",
doi = "10.18653/v1/2022.emnlp-main.740",
pages = "10775--10785",
abstract = "Large multilingual language models generally demonstrate impressive results in zero-shot cross-lingual transfer, yet often fail to successfully transfer to low-resource languages, even for token-level prediction tasks like named entity recognition (NER). In this work, we introduce a simple yet highly effective approach for improving zero-shot transfer for NER to low-resource languages. We observe that NER fine-tuning in the source language decontextualizes token representations, i.e., tokens increasingly attend to themselves. This increased reliance on token information itself, we hypothesize, triggers a type of overfitting to properties that NE tokens within the source languages share, but are generally not present in NE mentions of target languages. As a remedy, we propose a simple yet very effective sliced fine-tuning for NER (SLICER) that forces stronger token contextualization in the Transformer: we divide the transformed token representations and classifier into disjoint slices that are then independently classified during training. We evaluate SLICER on two standard benchmarks for NER that involve low-resource languages, WikiANN and MasakhaNER, and show that it (i) indeed reduces decontextualization (i.e., extent to which NE tokens attend to themselves), consequently (ii) yielding consistent transfer gains, especially prominent for low-resource target languages distant from the source language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schmidt-etal-2022-slicer">
<titleInfo>
<title>SLICER: Sliced Fine-Tuning for Low-Resource Cross-Lingual Transfer for Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fabian</namePart>
<namePart type="given">David</namePart>
<namePart type="family">Schmidt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vulić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Glavaš</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>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</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>Large multilingual language models generally demonstrate impressive results in zero-shot cross-lingual transfer, yet often fail to successfully transfer to low-resource languages, even for token-level prediction tasks like named entity recognition (NER). In this work, we introduce a simple yet highly effective approach for improving zero-shot transfer for NER to low-resource languages. We observe that NER fine-tuning in the source language decontextualizes token representations, i.e., tokens increasingly attend to themselves. This increased reliance on token information itself, we hypothesize, triggers a type of overfitting to properties that NE tokens within the source languages share, but are generally not present in NE mentions of target languages. As a remedy, we propose a simple yet very effective sliced fine-tuning for NER (SLICER) that forces stronger token contextualization in the Transformer: we divide the transformed token representations and classifier into disjoint slices that are then independently classified during training. We evaluate SLICER on two standard benchmarks for NER that involve low-resource languages, WikiANN and MasakhaNER, and show that it (i) indeed reduces decontextualization (i.e., extent to which NE tokens attend to themselves), consequently (ii) yielding consistent transfer gains, especially prominent for low-resource target languages distant from the source language.</abstract>
<identifier type="citekey">schmidt-etal-2022-slicer</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.740</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.740</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>10775</start>
<end>10785</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SLICER: Sliced Fine-Tuning for Low-Resource Cross-Lingual Transfer for Named Entity Recognition
%A Schmidt, Fabian David
%A Vulić, Ivan
%A Glavaš, Goran
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F schmidt-etal-2022-slicer
%X Large multilingual language models generally demonstrate impressive results in zero-shot cross-lingual transfer, yet often fail to successfully transfer to low-resource languages, even for token-level prediction tasks like named entity recognition (NER). In this work, we introduce a simple yet highly effective approach for improving zero-shot transfer for NER to low-resource languages. We observe that NER fine-tuning in the source language decontextualizes token representations, i.e., tokens increasingly attend to themselves. This increased reliance on token information itself, we hypothesize, triggers a type of overfitting to properties that NE tokens within the source languages share, but are generally not present in NE mentions of target languages. As a remedy, we propose a simple yet very effective sliced fine-tuning for NER (SLICER) that forces stronger token contextualization in the Transformer: we divide the transformed token representations and classifier into disjoint slices that are then independently classified during training. We evaluate SLICER on two standard benchmarks for NER that involve low-resource languages, WikiANN and MasakhaNER, and show that it (i) indeed reduces decontextualization (i.e., extent to which NE tokens attend to themselves), consequently (ii) yielding consistent transfer gains, especially prominent for low-resource target languages distant from the source language.
%R 10.18653/v1/2022.emnlp-main.740
%U https://aclanthology.org/2022.emnlp-main.740
%U https://doi.org/10.18653/v1/2022.emnlp-main.740
%P 10775-10785
Markdown (Informal)
[SLICER: Sliced Fine-Tuning for Low-Resource Cross-Lingual Transfer for Named Entity Recognition](https://aclanthology.org/2022.emnlp-main.740) (Schmidt et al., EMNLP 2022)
ACL