@inproceedings{choudhary-etal-2023-iitd,
title = "{IITD} at {S}em{E}val-2023 Task 2: A Multi-Stage Information Retrieval Approach for Fine-Grained Named Entity Recognition",
author = "Choudhary, Shivani and
Chatterjee, Niladri and
Saha, Subir",
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-1.111",
doi = "10.18653/v1/2023.semeval-1.111",
pages = "800--806",
abstract = "MultiCoNER-II is a fine-grained Named Entity Recognition (NER) task that aims to identify ambiguous and complex named entities in multiple languages, with a small amount of contextual information available. To address this task, we propose a multi-stage information retrieval (IR) pipeline that improves the performance of language models for fine-grained NER. Our approach involves leveraging a combination of a BM25-based IR model and a language model to retrieve relevant passages from a corpus. These passages are then used to train a model that utilizes a weighted average of losses. The prediction is generated by a decoder stack that includes a projection layer and conditional random field. To demonstrate the effectiveness of our approach, we participated in the English track of the MultiCoNER-II competition. Our approach yielded promising results, which we validated through detailed analysis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="choudhary-etal-2023-iitd">
<titleInfo>
<title>IITD at SemEval-2023 Task 2: A Multi-Stage Information Retrieval Approach for Fine-Grained Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shivani</namePart>
<namePart type="family">Choudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niladri</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subir</namePart>
<namePart type="family">Saha</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>MultiCoNER-II is a fine-grained Named Entity Recognition (NER) task that aims to identify ambiguous and complex named entities in multiple languages, with a small amount of contextual information available. To address this task, we propose a multi-stage information retrieval (IR) pipeline that improves the performance of language models for fine-grained NER. Our approach involves leveraging a combination of a BM25-based IR model and a language model to retrieve relevant passages from a corpus. These passages are then used to train a model that utilizes a weighted average of losses. The prediction is generated by a decoder stack that includes a projection layer and conditional random field. To demonstrate the effectiveness of our approach, we participated in the English track of the MultiCoNER-II competition. Our approach yielded promising results, which we validated through detailed analysis.</abstract>
<identifier type="citekey">choudhary-etal-2023-iitd</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.111</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.111</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>800</start>
<end>806</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IITD at SemEval-2023 Task 2: A Multi-Stage Information Retrieval Approach for Fine-Grained Named Entity Recognition
%A Choudhary, Shivani
%A Chatterjee, Niladri
%A Saha, Subir
%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 choudhary-etal-2023-iitd
%X MultiCoNER-II is a fine-grained Named Entity Recognition (NER) task that aims to identify ambiguous and complex named entities in multiple languages, with a small amount of contextual information available. To address this task, we propose a multi-stage information retrieval (IR) pipeline that improves the performance of language models for fine-grained NER. Our approach involves leveraging a combination of a BM25-based IR model and a language model to retrieve relevant passages from a corpus. These passages are then used to train a model that utilizes a weighted average of losses. The prediction is generated by a decoder stack that includes a projection layer and conditional random field. To demonstrate the effectiveness of our approach, we participated in the English track of the MultiCoNER-II competition. Our approach yielded promising results, which we validated through detailed analysis.
%R 10.18653/v1/2023.semeval-1.111
%U https://aclanthology.org/2023.semeval-1.111
%U https://doi.org/10.18653/v1/2023.semeval-1.111
%P 800-806
Markdown (Informal)
[IITD at SemEval-2023 Task 2: A Multi-Stage Information Retrieval Approach for Fine-Grained Named Entity Recognition](https://aclanthology.org/2023.semeval-1.111) (Choudhary et al., SemEval 2023)
ACL