@inproceedings{horne-etal-2020-grubert,
title = "{GRUBERT}: A {GRU}-Based Method to Fuse {BERT} Hidden Layers for {T}witter Sentiment Analysis",
author = "Horne, Leo and
Matti, Matthias and
Pourjafar, Pouya and
Wang, Zuowen",
editor = "Shmueli, Boaz and
Huang, Yin Jou",
booktitle = "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.aacl-srw.19",
pages = "130--138",
abstract = "In this work, we introduce a GRU-based architecture called GRUBERT that learns to map the different BERT hidden layers to fused embeddings with the aim of achieving high accuracy on the Twitter sentiment analysis task. Tweets are known for their highly diverse language, and by exploiting different linguistic information present across BERT hidden layers, we can capture the full extent of this language at the embedding level. Our method can be easily adapted to other embeddings capturing different linguistic information. We show that our method outperforms well-known heuristics of using BERT (e.g. using only the last layer) and other embeddings such as ELMo. We observe potential label noise resulting from the data acquisition process and employ early stopping as well as a voting classifier to overcome it.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="horne-etal-2020-grubert">
<titleInfo>
<title>GRUBERT: A GRU-Based Method to Fuse BERT Hidden Layers for Twitter Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Horne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Matti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pouya</namePart>
<namePart type="family">Pourjafar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zuowen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Boaz</namePart>
<namePart type="family">Shmueli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yin</namePart>
<namePart type="given">Jou</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we introduce a GRU-based architecture called GRUBERT that learns to map the different BERT hidden layers to fused embeddings with the aim of achieving high accuracy on the Twitter sentiment analysis task. Tweets are known for their highly diverse language, and by exploiting different linguistic information present across BERT hidden layers, we can capture the full extent of this language at the embedding level. Our method can be easily adapted to other embeddings capturing different linguistic information. We show that our method outperforms well-known heuristics of using BERT (e.g. using only the last layer) and other embeddings such as ELMo. We observe potential label noise resulting from the data acquisition process and employ early stopping as well as a voting classifier to overcome it.</abstract>
<identifier type="citekey">horne-etal-2020-grubert</identifier>
<location>
<url>https://aclanthology.org/2020.aacl-srw.19</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>130</start>
<end>138</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GRUBERT: A GRU-Based Method to Fuse BERT Hidden Layers for Twitter Sentiment Analysis
%A Horne, Leo
%A Matti, Matthias
%A Pourjafar, Pouya
%A Wang, Zuowen
%Y Shmueli, Boaz
%Y Huang, Yin Jou
%S Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop
%D 2020
%8 December
%I Association for Computational Linguistics
%C Suzhou, China
%F horne-etal-2020-grubert
%X In this work, we introduce a GRU-based architecture called GRUBERT that learns to map the different BERT hidden layers to fused embeddings with the aim of achieving high accuracy on the Twitter sentiment analysis task. Tweets are known for their highly diverse language, and by exploiting different linguistic information present across BERT hidden layers, we can capture the full extent of this language at the embedding level. Our method can be easily adapted to other embeddings capturing different linguistic information. We show that our method outperforms well-known heuristics of using BERT (e.g. using only the last layer) and other embeddings such as ELMo. We observe potential label noise resulting from the data acquisition process and employ early stopping as well as a voting classifier to overcome it.
%U https://aclanthology.org/2020.aacl-srw.19
%P 130-138
Markdown (Informal)
[GRUBERT: A GRU-Based Method to Fuse BERT Hidden Layers for Twitter Sentiment Analysis](https://aclanthology.org/2020.aacl-srw.19) (Horne et al., AACL 2020)
ACL
- Leo Horne, Matthias Matti, Pouya Pourjafar, and Zuowen Wang. 2020. GRUBERT: A GRU-Based Method to Fuse BERT Hidden Layers for Twitter Sentiment Analysis. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop, pages 130–138, Suzhou, China. Association for Computational Linguistics.