@inproceedings{sartipi-etal-2023-sartipi,
title = "Sartipi-Sedighin at {S}em{E}val-2023 Task 2: Fine-grained Named Entity Recognition with Pre-trained Contextual Language Models and Data Augmentation from {W}ikipedia",
author = "Sartipi, Amir and
Sedighin, Amirreza and
Fatemi, Afsaneh and
Baradaran Kashani, Hamidreza",
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-1.78",
doi = "10.18653/v1/2023.semeval-1.78",
pages = "565--579",
abstract = "This paper presents the system developed by the Sartipi-Sedighin team for SemEval 2023 Task 2, which is a shared task focused on multilingual complex named entity recognition (NER), or MultiCoNER II. The goal of this task is to identify and classify complex named entities (NEs) in text across multiple languages. To tackle the MultiCoNER II task, we leveraged pre-trained language models (PLMs) fine-tuned for each language included in the dataset. In addition, we also applied a data augmentation technique to increase the amount of training data available to our models. Specifically, we searched for relevant NEs that already existed in the training data within Wikipedia, and we added new instances of these entities to our training corpus. Our team achieved an overall F1 score of 61.25{\%} in the English track and 71.79{\%} in the multilingual track across all 13 tracks of the shared task that we submitted to.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sartipi-etal-2023-sartipi">
<titleInfo>
<title>Sartipi-Sedighin at SemEval-2023 Task 2: Fine-grained Named Entity Recognition with Pre-trained Contextual Language Models and Data Augmentation from Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Sartipi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amirreza</namePart>
<namePart type="family">Sedighin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afsaneh</namePart>
<namePart type="family">Fatemi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamidreza</namePart>
<namePart type="family">Baradaran Kashani</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 presents the system developed by the Sartipi-Sedighin team for SemEval 2023 Task 2, which is a shared task focused on multilingual complex named entity recognition (NER), or MultiCoNER II. The goal of this task is to identify and classify complex named entities (NEs) in text across multiple languages. To tackle the MultiCoNER II task, we leveraged pre-trained language models (PLMs) fine-tuned for each language included in the dataset. In addition, we also applied a data augmentation technique to increase the amount of training data available to our models. Specifically, we searched for relevant NEs that already existed in the training data within Wikipedia, and we added new instances of these entities to our training corpus. Our team achieved an overall F1 score of 61.25% in the English track and 71.79% in the multilingual track across all 13 tracks of the shared task that we submitted to.</abstract>
<identifier type="citekey">sartipi-etal-2023-sartipi</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.78</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.78</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>565</start>
<end>579</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sartipi-Sedighin at SemEval-2023 Task 2: Fine-grained Named Entity Recognition with Pre-trained Contextual Language Models and Data Augmentation from Wikipedia
%A Sartipi, Amir
%A Sedighin, Amirreza
%A Fatemi, Afsaneh
%A Baradaran Kashani, Hamidreza
%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 sartipi-etal-2023-sartipi
%X This paper presents the system developed by the Sartipi-Sedighin team for SemEval 2023 Task 2, which is a shared task focused on multilingual complex named entity recognition (NER), or MultiCoNER II. The goal of this task is to identify and classify complex named entities (NEs) in text across multiple languages. To tackle the MultiCoNER II task, we leveraged pre-trained language models (PLMs) fine-tuned for each language included in the dataset. In addition, we also applied a data augmentation technique to increase the amount of training data available to our models. Specifically, we searched for relevant NEs that already existed in the training data within Wikipedia, and we added new instances of these entities to our training corpus. Our team achieved an overall F1 score of 61.25% in the English track and 71.79% in the multilingual track across all 13 tracks of the shared task that we submitted to.
%R 10.18653/v1/2023.semeval-1.78
%U https://aclanthology.org/2023.semeval-1.78
%U https://doi.org/10.18653/v1/2023.semeval-1.78
%P 565-579
Markdown (Informal)
[Sartipi-Sedighin at SemEval-2023 Task 2: Fine-grained Named Entity Recognition with Pre-trained Contextual Language Models and Data Augmentation from Wikipedia](https://aclanthology.org/2023.semeval-1.78) (Sartipi et al., SemEval 2023)
ACL