@inproceedings{hossain-etal-2025-bigcat,
title = "{B}i{GCAT}: A Graph-Based Representation Learning Model with {LLM} Embeddings for Named Entity Recognition",
author = "Hossain, Md. Akram and
Aziz, Abdul and
Azim, Muhammad Anwarul and
Chy, Abu Nowshed and
Ullah, Md Zia and
Islam, Mohammad Khairul",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.52/",
pages = "433--440",
abstract = "Named entity recognition from financial text is challenging because of word ambiguity, huge quantity of unknown corporation names, and word abbreviation compared to nonfinancial text. However, models often treat named entities in a linear sequence fashion, which might obscure the model{'}s ability to capture complex hierarchical relationships among the entities. In this paper, we proposed a novel named entity recognition model BiGCAT, which integrates large language model (LLM) embeddings with graph-based representation where the contextual information captured by the language model and graph representation learning can complement each other. The method builds a spanning graph with nodes representing word spans and edges weighted by LLM embeddings, optimized using a combination of graph neural networks, specifically a graph-convolutional network (GCN) and a graph-attention network (GAT). This approach effectively captures the hierarchical dependencies among the spans. Our proposed model outperformed the state-of-the-art by 10{\%} and 18{\%} on the two publicly available datasets FiNER-ORD and FIN, respectively, in terms of weighted F1 score. The code is available at: https://github.com/Akram1871/BiGCAT-RANLP-2025."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hossain-etal-2025-bigcat">
<titleInfo>
<title>BiGCAT: A Graph-Based Representation Learning Model with LLM Embeddings for Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Akram</namePart>
<namePart type="family">Hossain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdul</namePart>
<namePart type="family">Aziz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Anwarul</namePart>
<namePart type="family">Azim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abu</namePart>
<namePart type="given">Nowshed</namePart>
<namePart type="family">Chy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Zia</namePart>
<namePart type="family">Ullah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Khairul</namePart>
<namePart type="family">Islam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Named entity recognition from financial text is challenging because of word ambiguity, huge quantity of unknown corporation names, and word abbreviation compared to nonfinancial text. However, models often treat named entities in a linear sequence fashion, which might obscure the model’s ability to capture complex hierarchical relationships among the entities. In this paper, we proposed a novel named entity recognition model BiGCAT, which integrates large language model (LLM) embeddings with graph-based representation where the contextual information captured by the language model and graph representation learning can complement each other. The method builds a spanning graph with nodes representing word spans and edges weighted by LLM embeddings, optimized using a combination of graph neural networks, specifically a graph-convolutional network (GCN) and a graph-attention network (GAT). This approach effectively captures the hierarchical dependencies among the spans. Our proposed model outperformed the state-of-the-art by 10% and 18% on the two publicly available datasets FiNER-ORD and FIN, respectively, in terms of weighted F1 score. The code is available at: https://github.com/Akram1871/BiGCAT-RANLP-2025.</abstract>
<identifier type="citekey">hossain-etal-2025-bigcat</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.52/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>433</start>
<end>440</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BiGCAT: A Graph-Based Representation Learning Model with LLM Embeddings for Named Entity Recognition
%A Hossain, Md. Akram
%A Aziz, Abdul
%A Azim, Muhammad Anwarul
%A Chy, Abu Nowshed
%A Ullah, Md Zia
%A Islam, Mohammad Khairul
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F hossain-etal-2025-bigcat
%X Named entity recognition from financial text is challenging because of word ambiguity, huge quantity of unknown corporation names, and word abbreviation compared to nonfinancial text. However, models often treat named entities in a linear sequence fashion, which might obscure the model’s ability to capture complex hierarchical relationships among the entities. In this paper, we proposed a novel named entity recognition model BiGCAT, which integrates large language model (LLM) embeddings with graph-based representation where the contextual information captured by the language model and graph representation learning can complement each other. The method builds a spanning graph with nodes representing word spans and edges weighted by LLM embeddings, optimized using a combination of graph neural networks, specifically a graph-convolutional network (GCN) and a graph-attention network (GAT). This approach effectively captures the hierarchical dependencies among the spans. Our proposed model outperformed the state-of-the-art by 10% and 18% on the two publicly available datasets FiNER-ORD and FIN, respectively, in terms of weighted F1 score. The code is available at: https://github.com/Akram1871/BiGCAT-RANLP-2025.
%U https://aclanthology.org/2025.ranlp-1.52/
%P 433-440
Markdown (Informal)
[BiGCAT: A Graph-Based Representation Learning Model with LLM Embeddings for Named Entity Recognition](https://aclanthology.org/2025.ranlp-1.52/) (Hossain et al., RANLP 2025)
ACL
- Md. Akram Hossain, Abdul Aziz, Muhammad Anwarul Azim, Abu Nowshed Chy, Md Zia Ullah, and Mohammad Khairul Islam. 2025. BiGCAT: A Graph-Based Representation Learning Model with LLM Embeddings for Named Entity Recognition. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 433–440, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.