@inproceedings{zou-li-2021-lz1904,
title = "{LZ}1904 at {S}em{E}val-2021 Task 5: {B}i-{LSTM}-{CRF} for Toxic Span Detection using Pretrained Word Embedding",
author = "Zou, Liang and
Li, Wen",
editor = "Palmer, Alexis and
Schneider, Nathan and
Schluter, Natalie and
Emerson, Guy and
Herbelot, Aurelie and
Zhu, Xiaodan",
booktitle = "Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.semeval-1.138",
doi = "10.18653/v1/2021.semeval-1.138",
pages = "1009--1014",
abstract = "Recurrent Neural Networks (RNN) have been widely used in various Natural Language Processing (NLP) tasks such as text classification, sequence tagging, and machine translation. Long Short Term Memory (LSTM), a special unit of RNN, has the benefit of memorizing past and even future information in a sentence (especially for bidirectional LSTM). In the shared task of detecting spans which make texts toxic, we first apply pretrained word embedding (GloVe) to generate the word vectors after tokenization. And then we construct Bidirectional Long Short Term Memory-Conditional Random Field (Bi-LSTM-CRF) model by Baidu research to predict whether each word in the sentence is toxic or not. We tune hyperparameters of dropout rate, number of LSTM units, embedding size with 10 epochs and choose the best epoch with validation recall. Our model achieves an F1 score of 66.99 percent in test dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zou-li-2021-lz1904">
<titleInfo>
<title>LZ1904 at SemEval-2021 Task 5: Bi-LSTM-CRF for Toxic Span Detection using Pretrained Word Embedding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recurrent Neural Networks (RNN) have been widely used in various Natural Language Processing (NLP) tasks such as text classification, sequence tagging, and machine translation. Long Short Term Memory (LSTM), a special unit of RNN, has the benefit of memorizing past and even future information in a sentence (especially for bidirectional LSTM). In the shared task of detecting spans which make texts toxic, we first apply pretrained word embedding (GloVe) to generate the word vectors after tokenization. And then we construct Bidirectional Long Short Term Memory-Conditional Random Field (Bi-LSTM-CRF) model by Baidu research to predict whether each word in the sentence is toxic or not. We tune hyperparameters of dropout rate, number of LSTM units, embedding size with 10 epochs and choose the best epoch with validation recall. Our model achieves an F1 score of 66.99 percent in test dataset.</abstract>
<identifier type="citekey">zou-li-2021-lz1904</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.138</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.138</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>1009</start>
<end>1014</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LZ1904 at SemEval-2021 Task 5: Bi-LSTM-CRF for Toxic Span Detection using Pretrained Word Embedding
%A Zou, Liang
%A Li, Wen
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Schluter, Natalie
%Y Emerson, Guy
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%S Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F zou-li-2021-lz1904
%X Recurrent Neural Networks (RNN) have been widely used in various Natural Language Processing (NLP) tasks such as text classification, sequence tagging, and machine translation. Long Short Term Memory (LSTM), a special unit of RNN, has the benefit of memorizing past and even future information in a sentence (especially for bidirectional LSTM). In the shared task of detecting spans which make texts toxic, we first apply pretrained word embedding (GloVe) to generate the word vectors after tokenization. And then we construct Bidirectional Long Short Term Memory-Conditional Random Field (Bi-LSTM-CRF) model by Baidu research to predict whether each word in the sentence is toxic or not. We tune hyperparameters of dropout rate, number of LSTM units, embedding size with 10 epochs and choose the best epoch with validation recall. Our model achieves an F1 score of 66.99 percent in test dataset.
%R 10.18653/v1/2021.semeval-1.138
%U https://aclanthology.org/2021.semeval-1.138
%U https://doi.org/10.18653/v1/2021.semeval-1.138
%P 1009-1014
Markdown (Informal)
[LZ1904 at SemEval-2021 Task 5: Bi-LSTM-CRF for Toxic Span Detection using Pretrained Word Embedding](https://aclanthology.org/2021.semeval-1.138) (Zou & Li, SemEval 2021)
ACL