@inproceedings{hu-etal-2021-risk,
title = "Risk Minimization for Zero-shot Sequence Labeling",
author = "Hu, Zechuan and
Jiang, Yong and
Bach, Nguyen and
Wang, Tao and
Huang, Zhongqiang and
Huang, Fei and
Tu, Kewei",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.380",
doi = "10.18653/v1/2021.acl-long.380",
pages = "4909--4920",
abstract = "Zero-shot sequence labeling aims to build a sequence labeler without human-annotated datasets. One straightforward approach is utilizing existing systems (source models) to generate pseudo-labeled datasets and train a target sequence labeler accordingly. However, due to the gap between the source and the target languages/domains, this approach may fail to recover the true labels. In this paper, we propose a novel unified framework for zero-shot sequence labeling with minimum risk training and design a new decomposable risk function that models the relations between the predicted labels from the source models and the true labels. By making the risk function trainable, we draw a connection between minimum risk training and latent variable model learning. We propose a unified learning algorithm based on the expectation maximization (EM) algorithm. We extensively evaluate our proposed approaches on cross-lingual/domain sequence labeling tasks over twenty-one datasets. The results show that our approaches outperform state-of-the-art baseline systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2021-risk">
<titleInfo>
<title>Risk Minimization for Zero-shot Sequence Labeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zechuan</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nguyen</namePart>
<namePart type="family">Bach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongqiang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kewei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Zero-shot sequence labeling aims to build a sequence labeler without human-annotated datasets. One straightforward approach is utilizing existing systems (source models) to generate pseudo-labeled datasets and train a target sequence labeler accordingly. However, due to the gap between the source and the target languages/domains, this approach may fail to recover the true labels. In this paper, we propose a novel unified framework for zero-shot sequence labeling with minimum risk training and design a new decomposable risk function that models the relations between the predicted labels from the source models and the true labels. By making the risk function trainable, we draw a connection between minimum risk training and latent variable model learning. We propose a unified learning algorithm based on the expectation maximization (EM) algorithm. We extensively evaluate our proposed approaches on cross-lingual/domain sequence labeling tasks over twenty-one datasets. The results show that our approaches outperform state-of-the-art baseline systems.</abstract>
<identifier type="citekey">hu-etal-2021-risk</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.380</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.380</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>4909</start>
<end>4920</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Risk Minimization for Zero-shot Sequence Labeling
%A Hu, Zechuan
%A Jiang, Yong
%A Bach, Nguyen
%A Wang, Tao
%A Huang, Zhongqiang
%A Huang, Fei
%A Tu, Kewei
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F hu-etal-2021-risk
%X Zero-shot sequence labeling aims to build a sequence labeler without human-annotated datasets. One straightforward approach is utilizing existing systems (source models) to generate pseudo-labeled datasets and train a target sequence labeler accordingly. However, due to the gap between the source and the target languages/domains, this approach may fail to recover the true labels. In this paper, we propose a novel unified framework for zero-shot sequence labeling with minimum risk training and design a new decomposable risk function that models the relations between the predicted labels from the source models and the true labels. By making the risk function trainable, we draw a connection between minimum risk training and latent variable model learning. We propose a unified learning algorithm based on the expectation maximization (EM) algorithm. We extensively evaluate our proposed approaches on cross-lingual/domain sequence labeling tasks over twenty-one datasets. The results show that our approaches outperform state-of-the-art baseline systems.
%R 10.18653/v1/2021.acl-long.380
%U https://aclanthology.org/2021.acl-long.380
%U https://doi.org/10.18653/v1/2021.acl-long.380
%P 4909-4920
Markdown (Informal)
[Risk Minimization for Zero-shot Sequence Labeling](https://aclanthology.org/2021.acl-long.380) (Hu et al., ACL-IJCNLP 2021)
ACL
- Zechuan Hu, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, and Kewei Tu. 2021. Risk Minimization for Zero-shot Sequence Labeling. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4909–4920, Online. Association for Computational Linguistics.