@inproceedings{gombert-bartsch-2021-tuda,
title = "{TUDA}-{CCL} at {S}em{E}val-2021 Task 1: Using Gradient-boosted Regression Tree Ensembles Trained on a Heterogeneous Feature Set for Predicting Lexical Complexity",
author = "Gombert, Sebastian and
Bartsch, Sabine",
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-1.12",
doi = "10.18653/v1/2021.semeval-1.12",
pages = "130--137",
abstract = "In this paper, we present our systems submitted to SemEval-2021 Task 1 on lexical complexity prediction. The aim of this shared task was to create systems able to predict the lexical complexity of word tokens and bigram multiword expressions within a given sentence context, a continuous value indicating the difficulty in understanding a respective utterance. Our approach relies on gradient boosted regression tree ensembles fitted using a heterogeneous feature set combining linguistic features, static and contextualized word embeddings, psycholinguistic norm lexica, WordNet, word- and character bigram frequencies and inclusion in wordlists to create a model able to assign a word or multiword expression a context-dependent complexity score. We can show that especially contextualised string embeddings can help with predicting lexical complexity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gombert-bartsch-2021-tuda">
<titleInfo>
<title>TUDA-CCL at SemEval-2021 Task 1: Using Gradient-boosted Regression Tree Ensembles Trained on a Heterogeneous Feature Set for Predicting Lexical Complexity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gombert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabine</namePart>
<namePart type="family">Bartsch</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>In this paper, we present our systems submitted to SemEval-2021 Task 1 on lexical complexity prediction. The aim of this shared task was to create systems able to predict the lexical complexity of word tokens and bigram multiword expressions within a given sentence context, a continuous value indicating the difficulty in understanding a respective utterance. Our approach relies on gradient boosted regression tree ensembles fitted using a heterogeneous feature set combining linguistic features, static and contextualized word embeddings, psycholinguistic norm lexica, WordNet, word- and character bigram frequencies and inclusion in wordlists to create a model able to assign a word or multiword expression a context-dependent complexity score. We can show that especially contextualised string embeddings can help with predicting lexical complexity.</abstract>
<identifier type="citekey">gombert-bartsch-2021-tuda</identifier>
<identifier type="doi">10.18653/v1/2021.semeval-1.12</identifier>
<location>
<url>https://aclanthology.org/2021.semeval-1.12</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>130</start>
<end>137</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TUDA-CCL at SemEval-2021 Task 1: Using Gradient-boosted Regression Tree Ensembles Trained on a Heterogeneous Feature Set for Predicting Lexical Complexity
%A Gombert, Sebastian
%A Bartsch, Sabine
%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 gombert-bartsch-2021-tuda
%X In this paper, we present our systems submitted to SemEval-2021 Task 1 on lexical complexity prediction. The aim of this shared task was to create systems able to predict the lexical complexity of word tokens and bigram multiword expressions within a given sentence context, a continuous value indicating the difficulty in understanding a respective utterance. Our approach relies on gradient boosted regression tree ensembles fitted using a heterogeneous feature set combining linguistic features, static and contextualized word embeddings, psycholinguistic norm lexica, WordNet, word- and character bigram frequencies and inclusion in wordlists to create a model able to assign a word or multiword expression a context-dependent complexity score. We can show that especially contextualised string embeddings can help with predicting lexical complexity.
%R 10.18653/v1/2021.semeval-1.12
%U https://aclanthology.org/2021.semeval-1.12
%U https://doi.org/10.18653/v1/2021.semeval-1.12
%P 130-137
Markdown (Informal)
[TUDA-CCL at SemEval-2021 Task 1: Using Gradient-boosted Regression Tree Ensembles Trained on a Heterogeneous Feature Set for Predicting Lexical Complexity](https://aclanthology.org/2021.semeval-1.12) (Gombert & Bartsch, SemEval 2021)
ACL