@inproceedings{marcinczuk-walentynowicz-2023-codenlp,
title = "{C}ode{NLP} at {S}em{E}val-2023 Task 2: Data Augmentation for Named Entity Recognition by Combination of Sequence Generation Strategies",
author = "Marci{\'n}czuk, Micha and
Walentynowicz, Wiktor",
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-1.249",
doi = "10.18653/v1/2023.semeval-1.249",
pages = "1798--1804",
abstract = "In the article, we present the CodeNLP submission to the SemEval-2023 Task 2: MultiCoNER II Multilingual Complex Named Entity Recognition. Our approach is based on data augmentation by combining various strategies of sequence generation for training. We show that the extended procedure of fine-tuning a pre-trained language model can bring improvements compared to any single strategy. On the development subsets, the improvements were 1.7 pp and 3.1 pp of F-measure, for English and multilingual datasets, respectively. On the test subsets our models achieved 63.51{\%} and 73.22{\%} of Macro F1, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marcinczuk-walentynowicz-2023-codenlp">
<titleInfo>
<title>CodeNLP at SemEval-2023 Task 2: Data Augmentation for Named Entity Recognition by Combination of Sequence Generation Strategies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Micha</namePart>
<namePart type="family">Marcińczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wiktor</namePart>
<namePart type="family">Walentynowicz</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>In the article, we present the CodeNLP submission to the SemEval-2023 Task 2: MultiCoNER II Multilingual Complex Named Entity Recognition. Our approach is based on data augmentation by combining various strategies of sequence generation for training. We show that the extended procedure of fine-tuning a pre-trained language model can bring improvements compared to any single strategy. On the development subsets, the improvements were 1.7 pp and 3.1 pp of F-measure, for English and multilingual datasets, respectively. On the test subsets our models achieved 63.51% and 73.22% of Macro F1, respectively.</abstract>
<identifier type="citekey">marcinczuk-walentynowicz-2023-codenlp</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.249</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.249</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1798</start>
<end>1804</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CodeNLP at SemEval-2023 Task 2: Data Augmentation for Named Entity Recognition by Combination of Sequence Generation Strategies
%A Marcińczuk, Micha
%A Walentynowicz, Wiktor
%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 marcinczuk-walentynowicz-2023-codenlp
%X In the article, we present the CodeNLP submission to the SemEval-2023 Task 2: MultiCoNER II Multilingual Complex Named Entity Recognition. Our approach is based on data augmentation by combining various strategies of sequence generation for training. We show that the extended procedure of fine-tuning a pre-trained language model can bring improvements compared to any single strategy. On the development subsets, the improvements were 1.7 pp and 3.1 pp of F-measure, for English and multilingual datasets, respectively. On the test subsets our models achieved 63.51% and 73.22% of Macro F1, respectively.
%R 10.18653/v1/2023.semeval-1.249
%U https://aclanthology.org/2023.semeval-1.249
%U https://doi.org/10.18653/v1/2023.semeval-1.249
%P 1798-1804
Markdown (Informal)
[CodeNLP at SemEval-2023 Task 2: Data Augmentation for Named Entity Recognition by Combination of Sequence Generation Strategies](https://aclanthology.org/2023.semeval-1.249) (Marcińczuk & Walentynowicz, SemEval 2023)
ACL