@inproceedings{wani-etal-2018-whole,
title = "The Whole is Greater than the Sum of its Parts: Towards the Effectiveness of Voting Ensemble Classifiers for Complex Word Identification",
author = "Wani, Nikhil and
Mathias, Sandeep and
Gajjam, Jayashree Aanand and
Bhattacharyya, Pushpak",
editor = "Tetreault, Joel and
Burstein, Jill and
Kochmar, Ekaterina and
Leacock, Claudia and
Yannakoudakis, Helen",
booktitle = "Proceedings of the Thirteenth Workshop on Innovative Use of {NLP} for Building Educational Applications",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-0522",
doi = "10.18653/v1/W18-0522",
pages = "200--205",
abstract = "In this paper, we present an effective system using voting ensemble classifiers to detect contextually complex words for non-native English speakers. To make the final decision, we channel a set of eight calibrated classifiers based on lexical, size and vocabulary features and train our model with annotated datasets collected from a mixture of native and non-native speakers. Thereafter, we test our system on three datasets namely News, WikiNews, and Wikipedia and report competitive results with an F1-Score ranging between 0.777 to 0.855 for each of the datasets. Our system outperforms multiple other models and falls within 0.042 to 0.026 percent of the best-performing model{'}s score in the shared task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wani-etal-2018-whole">
<titleInfo>
<title>The Whole is Greater than the Sum of its Parts: Towards the Effectiveness of Voting Ensemble Classifiers for Complex Word Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikhil</namePart>
<namePart type="family">Wani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandeep</namePart>
<namePart type="family">Mathias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jayashree</namePart>
<namePart type="given">Aanand</namePart>
<namePart type="family">Gajjam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Leacock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans, Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present an effective system using voting ensemble classifiers to detect contextually complex words for non-native English speakers. To make the final decision, we channel a set of eight calibrated classifiers based on lexical, size and vocabulary features and train our model with annotated datasets collected from a mixture of native and non-native speakers. Thereafter, we test our system on three datasets namely News, WikiNews, and Wikipedia and report competitive results with an F1-Score ranging between 0.777 to 0.855 for each of the datasets. Our system outperforms multiple other models and falls within 0.042 to 0.026 percent of the best-performing model’s score in the shared task.</abstract>
<identifier type="citekey">wani-etal-2018-whole</identifier>
<identifier type="doi">10.18653/v1/W18-0522</identifier>
<location>
<url>https://aclanthology.org/W18-0522</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>200</start>
<end>205</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Whole is Greater than the Sum of its Parts: Towards the Effectiveness of Voting Ensemble Classifiers for Complex Word Identification
%A Wani, Nikhil
%A Mathias, Sandeep
%A Gajjam, Jayashree Aanand
%A Bhattacharyya, Pushpak
%Y Tetreault, Joel
%Y Burstein, Jill
%Y Kochmar, Ekaterina
%Y Leacock, Claudia
%Y Yannakoudakis, Helen
%S Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F wani-etal-2018-whole
%X In this paper, we present an effective system using voting ensemble classifiers to detect contextually complex words for non-native English speakers. To make the final decision, we channel a set of eight calibrated classifiers based on lexical, size and vocabulary features and train our model with annotated datasets collected from a mixture of native and non-native speakers. Thereafter, we test our system on three datasets namely News, WikiNews, and Wikipedia and report competitive results with an F1-Score ranging between 0.777 to 0.855 for each of the datasets. Our system outperforms multiple other models and falls within 0.042 to 0.026 percent of the best-performing model’s score in the shared task.
%R 10.18653/v1/W18-0522
%U https://aclanthology.org/W18-0522
%U https://doi.org/10.18653/v1/W18-0522
%P 200-205
Markdown (Informal)
[The Whole is Greater than the Sum of its Parts: Towards the Effectiveness of Voting Ensemble Classifiers for Complex Word Identification](https://aclanthology.org/W18-0522) (Wani et al., BEA 2018)
ACL