@inproceedings{ferreira-vlachos-2019-incorporating,
title = "Incorporating Label Dependencies in Multilabel Stance Detection",
author = "Ferreira, William and
Vlachos, Andreas",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1665",
doi = "10.18653/v1/D19-1665",
pages = "6350--6354",
abstract = "Stance detection in social media is a well-studied task in a variety of domains. Nevertheless, previous work has mostly focused on multiclass versions of the problem, where the labels are mutually exclusive, and typically positive, negative or neutral. In this paper, we address versions of the task in which an utterance can have multiple labels, thus corresponding to multilabel classification. We propose a method that explicitly incorporates label dependencies in the training objective and compare it against a variety of baselines, as well as a reduction of multilabel to multiclass learning. In experiments with three datasets, we find that our proposed method improves upon all baselines on two out of three datasets. We also show that the reduction of multilabel to multiclass classification can be very competitive, especially in cases where the output consists of a small number of labels and one can enumerate over all label combinations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ferreira-vlachos-2019-incorporating">
<titleInfo>
<title>Incorporating Label Dependencies in Multilabel Stance Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Stance detection in social media is a well-studied task in a variety of domains. Nevertheless, previous work has mostly focused on multiclass versions of the problem, where the labels are mutually exclusive, and typically positive, negative or neutral. In this paper, we address versions of the task in which an utterance can have multiple labels, thus corresponding to multilabel classification. We propose a method that explicitly incorporates label dependencies in the training objective and compare it against a variety of baselines, as well as a reduction of multilabel to multiclass learning. In experiments with three datasets, we find that our proposed method improves upon all baselines on two out of three datasets. We also show that the reduction of multilabel to multiclass classification can be very competitive, especially in cases where the output consists of a small number of labels and one can enumerate over all label combinations.</abstract>
<identifier type="citekey">ferreira-vlachos-2019-incorporating</identifier>
<identifier type="doi">10.18653/v1/D19-1665</identifier>
<location>
<url>https://aclanthology.org/D19-1665</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>6350</start>
<end>6354</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Incorporating Label Dependencies in Multilabel Stance Detection
%A Ferreira, William
%A Vlachos, Andreas
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F ferreira-vlachos-2019-incorporating
%X Stance detection in social media is a well-studied task in a variety of domains. Nevertheless, previous work has mostly focused on multiclass versions of the problem, where the labels are mutually exclusive, and typically positive, negative or neutral. In this paper, we address versions of the task in which an utterance can have multiple labels, thus corresponding to multilabel classification. We propose a method that explicitly incorporates label dependencies in the training objective and compare it against a variety of baselines, as well as a reduction of multilabel to multiclass learning. In experiments with three datasets, we find that our proposed method improves upon all baselines on two out of three datasets. We also show that the reduction of multilabel to multiclass classification can be very competitive, especially in cases where the output consists of a small number of labels and one can enumerate over all label combinations.
%R 10.18653/v1/D19-1665
%U https://aclanthology.org/D19-1665
%U https://doi.org/10.18653/v1/D19-1665
%P 6350-6354
Markdown (Informal)
[Incorporating Label Dependencies in Multilabel Stance Detection](https://aclanthology.org/D19-1665) (Ferreira & Vlachos, EMNLP-IJCNLP 2019)
ACL
- William Ferreira and Andreas Vlachos. 2019. Incorporating Label Dependencies in Multilabel Stance Detection. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6350–6354, Hong Kong, China. Association for Computational Linguistics.