@inproceedings{wiedemann-etal-2019-uhh,
title = "{UHH}-{LT} at {S}em{E}val-2019 Task 6: Supervised vs. Unsupervised Transfer Learning for Offensive Language Detection",
author = "Wiedemann, Gregor and
Ruppert, Eugen and
Biemann, Chris",
editor = "May, Jonathan and
Shutova, Ekaterina and
Herbelot, Aurelie and
Zhu, Xiaodan and
Apidianaki, Marianna and
Mohammad, Saif M.",
booktitle = "Proceedings of the 13th International Workshop on Semantic Evaluation",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/S19-2137",
doi = "10.18653/v1/S19-2137",
pages = "782--787",
abstract = "We present a neural network based approach of transfer learning for offensive language detection. For our system, we compare two types of knowledge transfer: supervised and unsupervised pre-training. Supervised pre-training of our bidirectional GRU-3-CNN architecture is performed as multi-task learning of parallel training of five different tasks. The selected tasks are supervised classification problems from public NLP resources with some overlap to offensive language such as sentiment detection, emoji classification, and aggressive language classification. Unsupervised transfer learning is performed with a thematic clustering of 40M unlabeled tweets via LDA. Based on this dataset, pre-training is performed by predicting the main topic of a tweet. Results indicate that unsupervised transfer from large datasets performs slightly better than supervised training on small {`}near target category{'} datasets. In the SemEval Task, our system ranks 14 out of 103 participants.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wiedemann-etal-2019-uhh">
<titleInfo>
<title>UHH-LT at SemEval-2019 Task 6: Supervised vs. Unsupervised Transfer Learning for Offensive Language Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gregor</namePart>
<namePart type="family">Wiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugen</namePart>
<namePart type="family">Ruppert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Biemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th International Workshop on Semantic Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">May</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurelie</namePart>
<namePart type="family">Herbelot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saif</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Mohammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a neural network based approach of transfer learning for offensive language detection. For our system, we compare two types of knowledge transfer: supervised and unsupervised pre-training. Supervised pre-training of our bidirectional GRU-3-CNN architecture is performed as multi-task learning of parallel training of five different tasks. The selected tasks are supervised classification problems from public NLP resources with some overlap to offensive language such as sentiment detection, emoji classification, and aggressive language classification. Unsupervised transfer learning is performed with a thematic clustering of 40M unlabeled tweets via LDA. Based on this dataset, pre-training is performed by predicting the main topic of a tweet. Results indicate that unsupervised transfer from large datasets performs slightly better than supervised training on small ‘near target category’ datasets. In the SemEval Task, our system ranks 14 out of 103 participants.</abstract>
<identifier type="citekey">wiedemann-etal-2019-uhh</identifier>
<identifier type="doi">10.18653/v1/S19-2137</identifier>
<location>
<url>https://aclanthology.org/S19-2137</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>782</start>
<end>787</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UHH-LT at SemEval-2019 Task 6: Supervised vs. Unsupervised Transfer Learning for Offensive Language Detection
%A Wiedemann, Gregor
%A Ruppert, Eugen
%A Biemann, Chris
%Y May, Jonathan
%Y Shutova, Ekaterina
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%Y Apidianaki, Marianna
%Y Mohammad, Saif M.
%S Proceedings of the 13th International Workshop on Semantic Evaluation
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota, USA
%F wiedemann-etal-2019-uhh
%X We present a neural network based approach of transfer learning for offensive language detection. For our system, we compare two types of knowledge transfer: supervised and unsupervised pre-training. Supervised pre-training of our bidirectional GRU-3-CNN architecture is performed as multi-task learning of parallel training of five different tasks. The selected tasks are supervised classification problems from public NLP resources with some overlap to offensive language such as sentiment detection, emoji classification, and aggressive language classification. Unsupervised transfer learning is performed with a thematic clustering of 40M unlabeled tweets via LDA. Based on this dataset, pre-training is performed by predicting the main topic of a tweet. Results indicate that unsupervised transfer from large datasets performs slightly better than supervised training on small ‘near target category’ datasets. In the SemEval Task, our system ranks 14 out of 103 participants.
%R 10.18653/v1/S19-2137
%U https://aclanthology.org/S19-2137
%U https://doi.org/10.18653/v1/S19-2137
%P 782-787
Markdown (Informal)
[UHH-LT at SemEval-2019 Task 6: Supervised vs. Unsupervised Transfer Learning for Offensive Language Detection](https://aclanthology.org/S19-2137) (Wiedemann et al., SemEval 2019)
ACL