@inproceedings{stefanovitch-etal-2023-teamec,
title = "{T}eam{EC} at {S}em{E}val-2023 Task 4: Transformers vs. Low-Resource Dictionaries, Expert Dictionary vs. Learned Dictionary",
author = "Stefanovitch, Nicolas and
De Longueville, Bertrand and
Scharfbillig, Mario",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.290",
doi = "10.18653/v1/2023.semeval-1.290",
pages = "2107--2111",
abstract = "This paper describes the system we used to participate in the shared task, as well as additional experiments beyond the scope of the shared task, but using its data. Our primary goal is to compare the effectiveness of transformers model compared to low-resource dictionaries. Secondly, we compare the difference in performance of a learned dictionary and of a dictionary designed by experts in the field of values. Our findings surprisingly show that transformers perform on par with a dictionary containing less than 1k words, when evaluated with 19 fine-grained categories, and only outperform a dictionary-based approach in a coarse setting with 10 categories. Interestingly, the expert dictionary has a precision on par with the learned one, while its recall is clearly lower, potentially an indication of overfitting of topics to values in the shared task{'}s dataset. Our findings should be of interest to both the NLP and Value scientific communities on the use of automated approaches for value classification",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stefanovitch-etal-2023-teamec">
<titleInfo>
<title>TeamEC at SemEval-2023 Task 4: Transformers vs. Low-Resource Dictionaries, Expert Dictionary vs. Learned Dictionary</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Stefanovitch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bertrand</namePart>
<namePart type="family">De Longueville</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="family">Scharfbillig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Sartori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the system we used to participate in the shared task, as well as additional experiments beyond the scope of the shared task, but using its data. Our primary goal is to compare the effectiveness of transformers model compared to low-resource dictionaries. Secondly, we compare the difference in performance of a learned dictionary and of a dictionary designed by experts in the field of values. Our findings surprisingly show that transformers perform on par with a dictionary containing less than 1k words, when evaluated with 19 fine-grained categories, and only outperform a dictionary-based approach in a coarse setting with 10 categories. Interestingly, the expert dictionary has a precision on par with the learned one, while its recall is clearly lower, potentially an indication of overfitting of topics to values in the shared task’s dataset. Our findings should be of interest to both the NLP and Value scientific communities on the use of automated approaches for value classification</abstract>
<identifier type="citekey">stefanovitch-etal-2023-teamec</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.290</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.290</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>2107</start>
<end>2111</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TeamEC at SemEval-2023 Task 4: Transformers vs. Low-Resource Dictionaries, Expert Dictionary vs. Learned Dictionary
%A Stefanovitch, Nicolas
%A De Longueville, Bertrand
%A Scharfbillig, Mario
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F stefanovitch-etal-2023-teamec
%X This paper describes the system we used to participate in the shared task, as well as additional experiments beyond the scope of the shared task, but using its data. Our primary goal is to compare the effectiveness of transformers model compared to low-resource dictionaries. Secondly, we compare the difference in performance of a learned dictionary and of a dictionary designed by experts in the field of values. Our findings surprisingly show that transformers perform on par with a dictionary containing less than 1k words, when evaluated with 19 fine-grained categories, and only outperform a dictionary-based approach in a coarse setting with 10 categories. Interestingly, the expert dictionary has a precision on par with the learned one, while its recall is clearly lower, potentially an indication of overfitting of topics to values in the shared task’s dataset. Our findings should be of interest to both the NLP and Value scientific communities on the use of automated approaches for value classification
%R 10.18653/v1/2023.semeval-1.290
%U https://aclanthology.org/2023.semeval-1.290
%U https://doi.org/10.18653/v1/2023.semeval-1.290
%P 2107-2111
Markdown (Informal)
[TeamEC at SemEval-2023 Task 4: Transformers vs. Low-Resource Dictionaries, Expert Dictionary vs. Learned Dictionary](https://aclanthology.org/2023.semeval-1.290) (Stefanovitch et al., SemEval 2023)
ACL