@inproceedings{seganti-etal-2019-nlpr,
title = "{NLPR}@{SRPOL} at {S}em{E}val-2019 Task 6 and Task 5: Linguistically enhanced deep learning offensive sentence classifier",
author = "Seganti, Alessandro and
Sobol, Helena and
Orlova, Iryna and
Kim, Hannam and
Staniszewski, Jakub and
Krumholc, Tymoteusz and
Koziel, Krystian",
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/S19-2126/",
doi = "10.18653/v1/S19-2126",
pages = "712--721",
abstract = "The paper presents a system developed for the SemEval-2019 competition Task 5 hat- Eval Basile et al. (2019) (team name: LU Team) and Task 6 OffensEval Zampieri et al. (2019b) (team name: NLPR@SRPOL), where we achieved 2nd position in Subtask C. The system combines in an ensemble several models (LSTM, Transformer, OpenAI{'}s GPT, Random forest, SVM) with various embeddings (custom, ELMo, fastText, Universal Encoder) together with additional linguistic features (number of blacklisted words, special characters, etc.). The system works with a multi-tier blacklist and a large corpus of crawled data, annotated for general offensiveness. In the paper we do an extensive analysis of our results and show how the combination of features and embedding affect the performance of the models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seganti-etal-2019-nlpr">
<titleInfo>
<title>NLPR@SRPOL at SemEval-2019 Task 6 and Task 5: Linguistically enhanced deep learning offensive sentence classifier</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Seganti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Sobol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Orlova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannam</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Staniszewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tymoteusz</namePart>
<namePart type="family">Krumholc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krystian</namePart>
<namePart type="family">Koziel</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>The paper presents a system developed for the SemEval-2019 competition Task 5 hat- Eval Basile et al. (2019) (team name: LU Team) and Task 6 OffensEval Zampieri et al. (2019b) (team name: NLPR@SRPOL), where we achieved 2nd position in Subtask C. The system combines in an ensemble several models (LSTM, Transformer, OpenAI’s GPT, Random forest, SVM) with various embeddings (custom, ELMo, fastText, Universal Encoder) together with additional linguistic features (number of blacklisted words, special characters, etc.). The system works with a multi-tier blacklist and a large corpus of crawled data, annotated for general offensiveness. In the paper we do an extensive analysis of our results and show how the combination of features and embedding affect the performance of the models.</abstract>
<identifier type="citekey">seganti-etal-2019-nlpr</identifier>
<identifier type="doi">10.18653/v1/S19-2126</identifier>
<location>
<url>https://aclanthology.org/S19-2126/</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>712</start>
<end>721</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLPR@SRPOL at SemEval-2019 Task 6 and Task 5: Linguistically enhanced deep learning offensive sentence classifier
%A Seganti, Alessandro
%A Sobol, Helena
%A Orlova, Iryna
%A Kim, Hannam
%A Staniszewski, Jakub
%A Krumholc, Tymoteusz
%A Koziel, Krystian
%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 seganti-etal-2019-nlpr
%X The paper presents a system developed for the SemEval-2019 competition Task 5 hat- Eval Basile et al. (2019) (team name: LU Team) and Task 6 OffensEval Zampieri et al. (2019b) (team name: NLPR@SRPOL), where we achieved 2nd position in Subtask C. The system combines in an ensemble several models (LSTM, Transformer, OpenAI’s GPT, Random forest, SVM) with various embeddings (custom, ELMo, fastText, Universal Encoder) together with additional linguistic features (number of blacklisted words, special characters, etc.). The system works with a multi-tier blacklist and a large corpus of crawled data, annotated for general offensiveness. In the paper we do an extensive analysis of our results and show how the combination of features and embedding affect the performance of the models.
%R 10.18653/v1/S19-2126
%U https://aclanthology.org/S19-2126/
%U https://doi.org/10.18653/v1/S19-2126
%P 712-721
Markdown (Informal)
[NLPR@SRPOL at SemEval-2019 Task 6 and Task 5: Linguistically enhanced deep learning offensive sentence classifier](https://aclanthology.org/S19-2126/) (Seganti et al., SemEval 2019)
ACL
- Alessandro Seganti, Helena Sobol, Iryna Orlova, Hannam Kim, Jakub Staniszewski, Tymoteusz Krumholc, and Krystian Koziel. 2019. NLPR@SRPOL at SemEval-2019 Task 6 and Task 5: Linguistically enhanced deep learning offensive sentence classifier. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 712–721, Minneapolis, Minnesota, USA. Association for Computational Linguistics.