@inproceedings{lupancu-etal-2023-fii,
title = "{FII}{\_}{B}etter at {S}em{E}val-2023 Task 2: {M}ulti{C}o{NER} {II} Multilingual Complex Named Entity Recognition",
author = "Lupancu, Viorica-Camelia and
Platica, Alexandru-Gabriel and
Rosu, Cristian-Mihai and
Gifu, Daniela and
Trandabat, Diana",
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-1.153",
doi = "10.18653/v1/2023.semeval-1.153",
pages = "1107--1113",
abstract = "This task focuses on identifying complex named entities (NEs) in several languages. In the context of SemEval-2023 competition, our team presents an exploration of a base transformer model{'}s capabilities regarding the task, focused more specifically on five languages (English, Spanish, Swedish, German, Italian). We take DistilBERT and BERT as two examples of basic transformer models, using DistilBERT as a baseline and BERT as the platform to create an improved model. The dataset that we are using, MultiCoNER II, is a large multilingual dataset used for NER, that covers domains like: Wiki sentences, questions and search queries across 12 languages. This dataset contains 26M tokens and it is assembled from public resources. MultiCoNER II defines a NER tag-set with 6 classes and 67 tags. We have managed to get moderate results in the English track (we ranked 17th out of 34), while our results in the other tracks could be further improved in the future (overall third to last).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lupancu-etal-2023-fii">
<titleInfo>
<title>FII_Better at SemEval-2023 Task 2: MultiCoNER II Multilingual Complex Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Viorica-Camelia</namePart>
<namePart type="family">Lupancu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandru-Gabriel</namePart>
<namePart type="family">Platica</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristian-Mihai</namePart>
<namePart type="family">Rosu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniela</namePart>
<namePart type="family">Gifu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Trandabat</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 task focuses on identifying complex named entities (NEs) in several languages. In the context of SemEval-2023 competition, our team presents an exploration of a base transformer model’s capabilities regarding the task, focused more specifically on five languages (English, Spanish, Swedish, German, Italian). We take DistilBERT and BERT as two examples of basic transformer models, using DistilBERT as a baseline and BERT as the platform to create an improved model. The dataset that we are using, MultiCoNER II, is a large multilingual dataset used for NER, that covers domains like: Wiki sentences, questions and search queries across 12 languages. This dataset contains 26M tokens and it is assembled from public resources. MultiCoNER II defines a NER tag-set with 6 classes and 67 tags. We have managed to get moderate results in the English track (we ranked 17th out of 34), while our results in the other tracks could be further improved in the future (overall third to last).</abstract>
<identifier type="citekey">lupancu-etal-2023-fii</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.153</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.153</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1107</start>
<end>1113</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FII_Better at SemEval-2023 Task 2: MultiCoNER II Multilingual Complex Named Entity Recognition
%A Lupancu, Viorica-Camelia
%A Platica, Alexandru-Gabriel
%A Rosu, Cristian-Mihai
%A Gifu, Daniela
%A Trandabat, Diana
%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 lupancu-etal-2023-fii
%X This task focuses on identifying complex named entities (NEs) in several languages. In the context of SemEval-2023 competition, our team presents an exploration of a base transformer model’s capabilities regarding the task, focused more specifically on five languages (English, Spanish, Swedish, German, Italian). We take DistilBERT and BERT as two examples of basic transformer models, using DistilBERT as a baseline and BERT as the platform to create an improved model. The dataset that we are using, MultiCoNER II, is a large multilingual dataset used for NER, that covers domains like: Wiki sentences, questions and search queries across 12 languages. This dataset contains 26M tokens and it is assembled from public resources. MultiCoNER II defines a NER tag-set with 6 classes and 67 tags. We have managed to get moderate results in the English track (we ranked 17th out of 34), while our results in the other tracks could be further improved in the future (overall third to last).
%R 10.18653/v1/2023.semeval-1.153
%U https://aclanthology.org/2023.semeval-1.153
%U https://doi.org/10.18653/v1/2023.semeval-1.153
%P 1107-1113
Markdown (Informal)
[FII_Better at SemEval-2023 Task 2: MultiCoNER II Multilingual Complex Named Entity Recognition](https://aclanthology.org/2023.semeval-1.153) (Lupancu et al., SemEval 2023)
ACL