@inproceedings{bairaktaris-etal-2019-duth,
title = "{DUTH} at {S}em{E}val-2019 Task 8: Part-Of-Speech Features for Question Classification",
author = "Bairaktaris, Anastasios and
Symeonidis, Symeon and
Arampatzis, Avi",
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/S19-2202",
doi = "10.18653/v1/S19-2202",
pages = "1155--1159",
abstract = "This report describes the methods employed by the Democritus University of Thrace (DUTH) team for participating in SemEval-2019 Task 8: Fact Checking in Community Question Answering Forums. Our team dealt only with Subtask A: Question Classification. Our approach was based on shallow natural language processing (NLP) pre-processing techniques to reduce the noise in data, feature selection methods, and supervised machine learning algorithms such as NearestCentroid, Perceptron, and LinearSVC. To determine the essential features, we were aided by exploratory data analysis and visualizations. In order to improve classification accuracy, we developed a customized list of stopwords, retaining some opinion- and fact-denoting common function words which would have been removed by standard stoplisting. Furthermore, we examined the usefulness of part-of-speech (POS) categories for the task; by trying to remove nouns and adjectives, we found some evidence that verbs are a valuable POS category for the opinion question class.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bairaktaris-etal-2019-duth">
<titleInfo>
<title>DUTH at SemEval-2019 Task 8: Part-Of-Speech Features for Question Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anastasios</namePart>
<namePart type="family">Bairaktaris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Symeon</namePart>
<namePart type="family">Symeonidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avi</namePart>
<namePart type="family">Arampatzis</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>This report describes the methods employed by the Democritus University of Thrace (DUTH) team for participating in SemEval-2019 Task 8: Fact Checking in Community Question Answering Forums. Our team dealt only with Subtask A: Question Classification. Our approach was based on shallow natural language processing (NLP) pre-processing techniques to reduce the noise in data, feature selection methods, and supervised machine learning algorithms such as NearestCentroid, Perceptron, and LinearSVC. To determine the essential features, we were aided by exploratory data analysis and visualizations. In order to improve classification accuracy, we developed a customized list of stopwords, retaining some opinion- and fact-denoting common function words which would have been removed by standard stoplisting. Furthermore, we examined the usefulness of part-of-speech (POS) categories for the task; by trying to remove nouns and adjectives, we found some evidence that verbs are a valuable POS category for the opinion question class.</abstract>
<identifier type="citekey">bairaktaris-etal-2019-duth</identifier>
<identifier type="doi">10.18653/v1/S19-2202</identifier>
<location>
<url>https://aclanthology.org/S19-2202</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>1155</start>
<end>1159</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DUTH at SemEval-2019 Task 8: Part-Of-Speech Features for Question Classification
%A Bairaktaris, Anastasios
%A Symeonidis, Symeon
%A Arampatzis, Avi
%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 bairaktaris-etal-2019-duth
%X This report describes the methods employed by the Democritus University of Thrace (DUTH) team for participating in SemEval-2019 Task 8: Fact Checking in Community Question Answering Forums. Our team dealt only with Subtask A: Question Classification. Our approach was based on shallow natural language processing (NLP) pre-processing techniques to reduce the noise in data, feature selection methods, and supervised machine learning algorithms such as NearestCentroid, Perceptron, and LinearSVC. To determine the essential features, we were aided by exploratory data analysis and visualizations. In order to improve classification accuracy, we developed a customized list of stopwords, retaining some opinion- and fact-denoting common function words which would have been removed by standard stoplisting. Furthermore, we examined the usefulness of part-of-speech (POS) categories for the task; by trying to remove nouns and adjectives, we found some evidence that verbs are a valuable POS category for the opinion question class.
%R 10.18653/v1/S19-2202
%U https://aclanthology.org/S19-2202
%U https://doi.org/10.18653/v1/S19-2202
%P 1155-1159
Markdown (Informal)
[DUTH at SemEval-2019 Task 8: Part-Of-Speech Features for Question Classification](https://aclanthology.org/S19-2202) (Bairaktaris et al., SemEval 2019)
ACL