@inproceedings{wang-etal-2022-adaptive,
title = "Adaptive Unsupervised Self-training for Disfluency Detection",
author = "Wang, Zhongyuan and
Wang, Yixuan and
Wang, Shaolei and
Che, Wanxiang",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.632",
pages = "7209--7218",
abstract = "Supervised methods have achieved remarkable results in disfluency detection. However, in real-world scenarios, human-annotated data is difficult to obtain. Recent works try to handle disfluency detection with unsupervised self-training, which can exploit existing large-scale unlabeled data efficiently. However, their self-training-based methods suffer from the problems of selection bias and error accumulation. To tackle these problems, we propose an adaptive unsupervised self-training method for disfluency detection. Specifically, we re-weight the importance of each training example according to its grammatical feature and prediction confidence. Experiments on the Switchboard dataset show that our method improves 2.3 points over the current SOTA unsupervised method. Moreover, our method is competitive with the SOTA supervised method.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-adaptive">
<titleInfo>
<title>Adaptive Unsupervised Self-training for Disfluency Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhongyuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaolei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Supervised methods have achieved remarkable results in disfluency detection. However, in real-world scenarios, human-annotated data is difficult to obtain. Recent works try to handle disfluency detection with unsupervised self-training, which can exploit existing large-scale unlabeled data efficiently. However, their self-training-based methods suffer from the problems of selection bias and error accumulation. To tackle these problems, we propose an adaptive unsupervised self-training method for disfluency detection. Specifically, we re-weight the importance of each training example according to its grammatical feature and prediction confidence. Experiments on the Switchboard dataset show that our method improves 2.3 points over the current SOTA unsupervised method. Moreover, our method is competitive with the SOTA supervised method.</abstract>
<identifier type="citekey">wang-etal-2022-adaptive</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.632</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>7209</start>
<end>7218</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adaptive Unsupervised Self-training for Disfluency Detection
%A Wang, Zhongyuan
%A Wang, Yixuan
%A Wang, Shaolei
%A Che, Wanxiang
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F wang-etal-2022-adaptive
%X Supervised methods have achieved remarkable results in disfluency detection. However, in real-world scenarios, human-annotated data is difficult to obtain. Recent works try to handle disfluency detection with unsupervised self-training, which can exploit existing large-scale unlabeled data efficiently. However, their self-training-based methods suffer from the problems of selection bias and error accumulation. To tackle these problems, we propose an adaptive unsupervised self-training method for disfluency detection. Specifically, we re-weight the importance of each training example according to its grammatical feature and prediction confidence. Experiments on the Switchboard dataset show that our method improves 2.3 points over the current SOTA unsupervised method. Moreover, our method is competitive with the SOTA supervised method.
%U https://aclanthology.org/2022.coling-1.632
%P 7209-7218
Markdown (Informal)
[Adaptive Unsupervised Self-training for Disfluency Detection](https://aclanthology.org/2022.coling-1.632) (Wang et al., COLING 2022)
ACL
- Zhongyuan Wang, Yixuan Wang, Shaolei Wang, and Wanxiang Che. 2022. Adaptive Unsupervised Self-training for Disfluency Detection. In Proceedings of the 29th International Conference on Computational Linguistics, pages 7209–7218, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.