@inproceedings{li-etal-2021-improving-stance,
title = "Improving Stance Detection with Multi-Dataset Learning and Knowledge Distillation",
author = "Li, Yingjie and
Zhao, Chenye and
Caragea, Cornelia",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.511",
doi = "10.18653/v1/2021.emnlp-main.511",
pages = "6332--6345",
abstract = "Stance detection determines whether the author of a text is in favor of, against or neutral to a specific target and provides valuable insights into important events such as legalization of abortion. Despite significant progress on this task, one of the remaining challenges is the scarcity of annotations. Besides, most previous works focused on a hard-label training in which meaningful similarities among categories are discarded during training. To address these challenges, first, we evaluate a multi-target and a multi-dataset training settings by training one model on each dataset and datasets of different domains, respectively. We show that models can learn more universal representations with respect to targets in these settings. Second, we investigate the knowledge distillation in stance detection and observe that transferring knowledge from a teacher model to a student model can be beneficial in our proposed training settings. Moreover, we propose an Adaptive Knowledge Distillation (AKD) method that applies instance-specific temperature scaling to the teacher and student predictions. Results show that the multi-dataset model performs best on all datasets and it can be further improved by the proposed AKD, outperforming the state-of-the-art by a large margin. We publicly release our code.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2021-improving-stance">
<titleInfo>
<title>Improving Stance Detection with Multi-Dataset Learning and Knowledge Distillation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yingjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenye</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cornelia</namePart>
<namePart type="family">Caragea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Stance detection determines whether the author of a text is in favor of, against or neutral to a specific target and provides valuable insights into important events such as legalization of abortion. Despite significant progress on this task, one of the remaining challenges is the scarcity of annotations. Besides, most previous works focused on a hard-label training in which meaningful similarities among categories are discarded during training. To address these challenges, first, we evaluate a multi-target and a multi-dataset training settings by training one model on each dataset and datasets of different domains, respectively. We show that models can learn more universal representations with respect to targets in these settings. Second, we investigate the knowledge distillation in stance detection and observe that transferring knowledge from a teacher model to a student model can be beneficial in our proposed training settings. Moreover, we propose an Adaptive Knowledge Distillation (AKD) method that applies instance-specific temperature scaling to the teacher and student predictions. Results show that the multi-dataset model performs best on all datasets and it can be further improved by the proposed AKD, outperforming the state-of-the-art by a large margin. We publicly release our code.</abstract>
<identifier type="citekey">li-etal-2021-improving-stance</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.511</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.511</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>6332</start>
<end>6345</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Stance Detection with Multi-Dataset Learning and Knowledge Distillation
%A Li, Yingjie
%A Zhao, Chenye
%A Caragea, Cornelia
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F li-etal-2021-improving-stance
%X Stance detection determines whether the author of a text is in favor of, against or neutral to a specific target and provides valuable insights into important events such as legalization of abortion. Despite significant progress on this task, one of the remaining challenges is the scarcity of annotations. Besides, most previous works focused on a hard-label training in which meaningful similarities among categories are discarded during training. To address these challenges, first, we evaluate a multi-target and a multi-dataset training settings by training one model on each dataset and datasets of different domains, respectively. We show that models can learn more universal representations with respect to targets in these settings. Second, we investigate the knowledge distillation in stance detection and observe that transferring knowledge from a teacher model to a student model can be beneficial in our proposed training settings. Moreover, we propose an Adaptive Knowledge Distillation (AKD) method that applies instance-specific temperature scaling to the teacher and student predictions. Results show that the multi-dataset model performs best on all datasets and it can be further improved by the proposed AKD, outperforming the state-of-the-art by a large margin. We publicly release our code.
%R 10.18653/v1/2021.emnlp-main.511
%U https://aclanthology.org/2021.emnlp-main.511
%U https://doi.org/10.18653/v1/2021.emnlp-main.511
%P 6332-6345
Markdown (Informal)
[Improving Stance Detection with Multi-Dataset Learning and Knowledge Distillation](https://aclanthology.org/2021.emnlp-main.511) (Li et al., EMNLP 2021)
ACL