@inproceedings{meng-etal-2017-qlut,
title = "{QLUT} at {S}em{E}val-2017 Task 1: Semantic Textual Similarity Based on Word Embeddings",
author = "Meng, Fanqing and
Lu, Wenpeng and
Zhang, Yuteng and
Cheng, Jinyong and
Du, Yuehan and
Han, Shuwang",
editor = "Bethard, Steven and
Carpuat, Marine and
Apidianaki, Marianna and
Mohammad, Saif M. and
Cer, Daniel and
Jurgens, David",
booktitle = "Proceedings of the 11th International Workshop on Semantic Evaluation ({S}em{E}val-2017)",
month = aug,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/S17-2020",
doi = "10.18653/v1/S17-2020",
pages = "150--153",
abstract = "This paper reports the details of our submissions in the task 1 of SemEval 2017. This task aims at assessing the semantic textual similarity of two sentences or texts. We submit three unsupervised systems based on word embeddings. The differences between these runs are the various preprocessing on evaluation data. The best performance of these systems on the evaluation of Pearson correlation is 0.6887. Unsurprisingly, results of our runs demonstrate that data preprocessing, such as tokenization, lemmatization, extraction of content words and removing stop words, is helpful and plays a significant role in improving the performance of models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meng-etal-2017-qlut">
<titleInfo>
<title>QLUT at SemEval-2017 Task 1: Semantic Textual Similarity Based on Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fanqing</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenpeng</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuteng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinyong</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuehan</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuwang</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)</title>
</titleInfo>
<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">Marine</namePart>
<namePart type="family">Carpuat</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>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Cer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper reports the details of our submissions in the task 1 of SemEval 2017. This task aims at assessing the semantic textual similarity of two sentences or texts. We submit three unsupervised systems based on word embeddings. The differences between these runs are the various preprocessing on evaluation data. The best performance of these systems on the evaluation of Pearson correlation is 0.6887. Unsurprisingly, results of our runs demonstrate that data preprocessing, such as tokenization, lemmatization, extraction of content words and removing stop words, is helpful and plays a significant role in improving the performance of models.</abstract>
<identifier type="citekey">meng-etal-2017-qlut</identifier>
<identifier type="doi">10.18653/v1/S17-2020</identifier>
<location>
<url>https://aclanthology.org/S17-2020</url>
</location>
<part>
<date>2017-08</date>
<extent unit="page">
<start>150</start>
<end>153</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QLUT at SemEval-2017 Task 1: Semantic Textual Similarity Based on Word Embeddings
%A Meng, Fanqing
%A Lu, Wenpeng
%A Zhang, Yuteng
%A Cheng, Jinyong
%A Du, Yuehan
%A Han, Shuwang
%Y Bethard, Steven
%Y Carpuat, Marine
%Y Apidianaki, Marianna
%Y Mohammad, Saif M.
%Y Cer, Daniel
%Y Jurgens, David
%S Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)
%D 2017
%8 August
%I Association for Computational Linguistics
%C Vancouver, Canada
%F meng-etal-2017-qlut
%X This paper reports the details of our submissions in the task 1 of SemEval 2017. This task aims at assessing the semantic textual similarity of two sentences or texts. We submit three unsupervised systems based on word embeddings. The differences between these runs are the various preprocessing on evaluation data. The best performance of these systems on the evaluation of Pearson correlation is 0.6887. Unsurprisingly, results of our runs demonstrate that data preprocessing, such as tokenization, lemmatization, extraction of content words and removing stop words, is helpful and plays a significant role in improving the performance of models.
%R 10.18653/v1/S17-2020
%U https://aclanthology.org/S17-2020
%U https://doi.org/10.18653/v1/S17-2020
%P 150-153
Markdown (Informal)
[QLUT at SemEval-2017 Task 1: Semantic Textual Similarity Based on Word Embeddings](https://aclanthology.org/S17-2020) (Meng et al., SemEval 2017)
ACL