@inproceedings{poumay-ittoo-2021-comprehensive-comparison,
title = "A {C}omprehensive {C}omparison of {W}ord {E}mbeddings in {E}vent {\&} {E}ntity {C}oreference {R}esolution.",
author = "Poumay, Judicael and
Ittoo, Ashwin",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.235",
doi = "10.18653/v1/2021.findings-emnlp.235",
pages = "2755--2764",
abstract = "Coreference Resolution is an important NLP task and most state-of-the-art methods rely on word embeddings for word representation. However, one issue that has been largely overlooked in literature is that of comparing the performance of different embeddings across and within families. Therefore, we frame our study in the context of Event and Entity Coreference Resolution (EvCR {\&} EnCR), and address two questions : 1) Is there a trade-off between performance (predictive and run-time) and embedding size? 2) How do the embeddings{'} performance compare within and across families? Our experiments reveal several interesting findings. First, we observe diminishing returns in performance with respect to embedding size. E.g. a model using solely a character embedding achieves 86{\%} of the performance of the largest model (Elmo, GloVe, Character) while being 1.2{\%} of its size. Second, the larger models using multiple embeddings learns faster despite being slower per epoch. However, it is still slower at test time. Finally, Elmo performs best on both EvCR and EnCR, while GloVe and FastText perform best in EvCR and EnCR respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="poumay-ittoo-2021-comprehensive-comparison">
<titleInfo>
<title>A Comprehensive Comparison of Word Embeddings in Event & Entity Coreference Resolution.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Judicael</namePart>
<namePart type="family">Poumay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashwin</namePart>
<namePart type="family">Ittoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Coreference Resolution is an important NLP task and most state-of-the-art methods rely on word embeddings for word representation. However, one issue that has been largely overlooked in literature is that of comparing the performance of different embeddings across and within families. Therefore, we frame our study in the context of Event and Entity Coreference Resolution (EvCR & EnCR), and address two questions : 1) Is there a trade-off between performance (predictive and run-time) and embedding size? 2) How do the embeddings’ performance compare within and across families? Our experiments reveal several interesting findings. First, we observe diminishing returns in performance with respect to embedding size. E.g. a model using solely a character embedding achieves 86% of the performance of the largest model (Elmo, GloVe, Character) while being 1.2% of its size. Second, the larger models using multiple embeddings learns faster despite being slower per epoch. However, it is still slower at test time. Finally, Elmo performs best on both EvCR and EnCR, while GloVe and FastText perform best in EvCR and EnCR respectively.</abstract>
<identifier type="citekey">poumay-ittoo-2021-comprehensive-comparison</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.235</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.235</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>2755</start>
<end>2764</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Comprehensive Comparison of Word Embeddings in Event & Entity Coreference Resolution.
%A Poumay, Judicael
%A Ittoo, Ashwin
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F poumay-ittoo-2021-comprehensive-comparison
%X Coreference Resolution is an important NLP task and most state-of-the-art methods rely on word embeddings for word representation. However, one issue that has been largely overlooked in literature is that of comparing the performance of different embeddings across and within families. Therefore, we frame our study in the context of Event and Entity Coreference Resolution (EvCR & EnCR), and address two questions : 1) Is there a trade-off between performance (predictive and run-time) and embedding size? 2) How do the embeddings’ performance compare within and across families? Our experiments reveal several interesting findings. First, we observe diminishing returns in performance with respect to embedding size. E.g. a model using solely a character embedding achieves 86% of the performance of the largest model (Elmo, GloVe, Character) while being 1.2% of its size. Second, the larger models using multiple embeddings learns faster despite being slower per epoch. However, it is still slower at test time. Finally, Elmo performs best on both EvCR and EnCR, while GloVe and FastText perform best in EvCR and EnCR respectively.
%R 10.18653/v1/2021.findings-emnlp.235
%U https://aclanthology.org/2021.findings-emnlp.235
%U https://doi.org/10.18653/v1/2021.findings-emnlp.235
%P 2755-2764
Markdown (Informal)
[A Comprehensive Comparison of Word Embeddings in Event & Entity Coreference Resolution.](https://aclanthology.org/2021.findings-emnlp.235) (Poumay & Ittoo, Findings 2021)
ACL