@inproceedings{gui-etal-2020-uncertainty,
title = "Uncertainty-Aware Label Refinement for Sequence Labeling",
author = "Gui, Tao and
Ye, Jiacheng and
Zhang, Qi and
Li, Zhengyan and
Fei, Zichu and
Gong, Yeyun and
Huang, Xuanjing",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.181",
doi = "10.18653/v1/2020.emnlp-main.181",
pages = "2316--2326",
abstract = "Conditional random fields (CRF) for label decoding has become ubiquitous in sequence labeling tasks. However, the local label dependencies and inefficient Viterbi decoding have always been a problem to be solved. In this work, we introduce a novel two-stage label decoding framework to model long-term label dependencies, while being much more computationally efficient. A base model first predicts draft labels, and then a novel two-stream self-attention model makes refinements on these draft predictions based on long-range label dependencies, which can achieve parallel decoding for a faster prediction. In addition, in order to mitigate the side effects of incorrect draft labels, Bayesian neural networks are used to indicate the labels with a high probability of being wrong, which can greatly assist in preventing error propagation. The experimental results on three sequence labeling benchmarks demonstrated that the proposed method not only outperformed the CRF-based methods but also greatly accelerated the inference process.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gui-etal-2020-uncertainty">
<titleInfo>
<title>Uncertainty-Aware Label Refinement for Sequence Labeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Gui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiacheng</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengyan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zichu</namePart>
<namePart type="family">Fei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yeyun</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Conditional random fields (CRF) for label decoding has become ubiquitous in sequence labeling tasks. However, the local label dependencies and inefficient Viterbi decoding have always been a problem to be solved. In this work, we introduce a novel two-stage label decoding framework to model long-term label dependencies, while being much more computationally efficient. A base model first predicts draft labels, and then a novel two-stream self-attention model makes refinements on these draft predictions based on long-range label dependencies, which can achieve parallel decoding for a faster prediction. In addition, in order to mitigate the side effects of incorrect draft labels, Bayesian neural networks are used to indicate the labels with a high probability of being wrong, which can greatly assist in preventing error propagation. The experimental results on three sequence labeling benchmarks demonstrated that the proposed method not only outperformed the CRF-based methods but also greatly accelerated the inference process.</abstract>
<identifier type="citekey">gui-etal-2020-uncertainty</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.181</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.181</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>2316</start>
<end>2326</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Uncertainty-Aware Label Refinement for Sequence Labeling
%A Gui, Tao
%A Ye, Jiacheng
%A Zhang, Qi
%A Li, Zhengyan
%A Fei, Zichu
%A Gong, Yeyun
%A Huang, Xuanjing
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F gui-etal-2020-uncertainty
%X Conditional random fields (CRF) for label decoding has become ubiquitous in sequence labeling tasks. However, the local label dependencies and inefficient Viterbi decoding have always been a problem to be solved. In this work, we introduce a novel two-stage label decoding framework to model long-term label dependencies, while being much more computationally efficient. A base model first predicts draft labels, and then a novel two-stream self-attention model makes refinements on these draft predictions based on long-range label dependencies, which can achieve parallel decoding for a faster prediction. In addition, in order to mitigate the side effects of incorrect draft labels, Bayesian neural networks are used to indicate the labels with a high probability of being wrong, which can greatly assist in preventing error propagation. The experimental results on three sequence labeling benchmarks demonstrated that the proposed method not only outperformed the CRF-based methods but also greatly accelerated the inference process.
%R 10.18653/v1/2020.emnlp-main.181
%U https://aclanthology.org/2020.emnlp-main.181
%U https://doi.org/10.18653/v1/2020.emnlp-main.181
%P 2316-2326
Markdown (Informal)
[Uncertainty-Aware Label Refinement for Sequence Labeling](https://aclanthology.org/2020.emnlp-main.181) (Gui et al., EMNLP 2020)
ACL
- Tao Gui, Jiacheng Ye, Qi Zhang, Zhengyan Li, Zichu Fei, Yeyun Gong, and Xuanjing Huang. 2020. Uncertainty-Aware Label Refinement for Sequence Labeling. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2316–2326, Online. Association for Computational Linguistics.