@inproceedings{kawintiranon-singh-2021-knowledge,
title = "Knowledge Enhanced Masked Language Model for Stance Detection",
author = "Kawintiranon, Kornraphop and
Singh, Lisa",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.376/",
doi = "10.18653/v1/2021.naacl-main.376",
pages = "4725--4735",
abstract = "Detecting stance on Twitter is especially challenging because of the short length of each tweet, the continuous coinage of new terminology and hashtags, and the deviation of sentence structure from standard prose. Fine-tuned language models using large-scale in-domain data have been shown to be the new state-of-the-art for many NLP tasks, including stance detection. In this paper, we propose a novel BERT-based fine-tuning method that enhances the masked language model for stance detection. Instead of random token masking, we propose using a weighted log-odds-ratio to identify words with high stance distinguishability and then model an attention mechanism that focuses on these words. We show that our proposed approach outperforms the state of the art for stance detection on Twitter data about the 2020 US Presidential election."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kawintiranon-singh-2021-knowledge">
<titleInfo>
<title>Knowledge Enhanced Masked Language Model for Stance Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kornraphop</namePart>
<namePart type="family">Kawintiranon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</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>Detecting stance on Twitter is especially challenging because of the short length of each tweet, the continuous coinage of new terminology and hashtags, and the deviation of sentence structure from standard prose. Fine-tuned language models using large-scale in-domain data have been shown to be the new state-of-the-art for many NLP tasks, including stance detection. In this paper, we propose a novel BERT-based fine-tuning method that enhances the masked language model for stance detection. Instead of random token masking, we propose using a weighted log-odds-ratio to identify words with high stance distinguishability and then model an attention mechanism that focuses on these words. We show that our proposed approach outperforms the state of the art for stance detection on Twitter data about the 2020 US Presidential election.</abstract>
<identifier type="citekey">kawintiranon-singh-2021-knowledge</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.376</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.376/</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>4725</start>
<end>4735</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowledge Enhanced Masked Language Model for Stance Detection
%A Kawintiranon, Kornraphop
%A Singh, Lisa
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F kawintiranon-singh-2021-knowledge
%X Detecting stance on Twitter is especially challenging because of the short length of each tweet, the continuous coinage of new terminology and hashtags, and the deviation of sentence structure from standard prose. Fine-tuned language models using large-scale in-domain data have been shown to be the new state-of-the-art for many NLP tasks, including stance detection. In this paper, we propose a novel BERT-based fine-tuning method that enhances the masked language model for stance detection. Instead of random token masking, we propose using a weighted log-odds-ratio to identify words with high stance distinguishability and then model an attention mechanism that focuses on these words. We show that our proposed approach outperforms the state of the art for stance detection on Twitter data about the 2020 US Presidential election.
%R 10.18653/v1/2021.naacl-main.376
%U https://aclanthology.org/2021.naacl-main.376/
%U https://doi.org/10.18653/v1/2021.naacl-main.376
%P 4725-4735
Markdown (Informal)
[Knowledge Enhanced Masked Language Model for Stance Detection](https://aclanthology.org/2021.naacl-main.376/) (Kawintiranon & Singh, NAACL 2021)
ACL
- Kornraphop Kawintiranon and Lisa Singh. 2021. Knowledge Enhanced Masked Language Model for Stance Detection. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4725–4735, Online. Association for Computational Linguistics.