@inproceedings{purbey-etal-2025-1-800-shared,
title = "1-800-{SHARED}-{TASKS} at {R}eg{NLP}: Lexical Reranking of Semantic Retrieval ({L}e{S}e{R}) for Regulatory Question Answering",
author = "Purbey, Jebish and
Sharma, Drishti and
Gupta, Siddhant and
Murad, Khawaja and
Pullakhandam, Siddartha and
Kadiyala, Ram Mohan Rao",
editor = "Gokhan, Tuba and
Wang, Kexin and
Gurevych, Iryna and
Briscoe, Ted",
booktitle = "Proceedings of the 1st Regulatory NLP Workshop (RegNLP 2025)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.regnlp-1.6/",
pages = "36--40",
abstract = "This paper presents the system description of our entry for the COLING 2025 RegNLP RIRAG (Regulatory Information Retrieval and Answer Generation) challenge, focusing on leveraging advanced information retrieval and answer generation techniques in regulatory domains. We experimented with a combination of embedding models, including Stella, BGE, CDE, and Mpnet, and leveraged fine-tuning and reranking for retrieving relevant documents in top ranks. We utilized a novel approach, LeSeR, which achieved competitive results with a recall@10 of 0.8201 and map@10 of 0.6655 for retrievals. This work highlights the transformative potential of natural language processing techniques in regulatory applications, offering insights into their capabilities for implementing a retrieval augmented generation system while identifying areas for future improvement in robustness and domain adaptation."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="purbey-etal-2025-1-800-shared">
<titleInfo>
<title>1-800-SHARED-TASKS at RegNLP: Lexical Reranking of Semantic Retrieval (LeSeR) for Regulatory Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jebish</namePart>
<namePart type="family">Purbey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Drishti</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddhant</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khawaja</namePart>
<namePart type="family">Murad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddartha</namePart>
<namePart type="family">Pullakhandam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ram</namePart>
<namePart type="given">Mohan</namePart>
<namePart type="given">Rao</namePart>
<namePart type="family">Kadiyala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Regulatory NLP Workshop (RegNLP 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tuba</namePart>
<namePart type="family">Gokhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kexin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ted</namePart>
<namePart type="family">Briscoe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the system description of our entry for the COLING 2025 RegNLP RIRAG (Regulatory Information Retrieval and Answer Generation) challenge, focusing on leveraging advanced information retrieval and answer generation techniques in regulatory domains. We experimented with a combination of embedding models, including Stella, BGE, CDE, and Mpnet, and leveraged fine-tuning and reranking for retrieving relevant documents in top ranks. We utilized a novel approach, LeSeR, which achieved competitive results with a recall@10 of 0.8201 and map@10 of 0.6655 for retrievals. This work highlights the transformative potential of natural language processing techniques in regulatory applications, offering insights into their capabilities for implementing a retrieval augmented generation system while identifying areas for future improvement in robustness and domain adaptation.</abstract>
<identifier type="citekey">purbey-etal-2025-1-800-shared</identifier>
<location>
<url>https://aclanthology.org/2025.regnlp-1.6/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>36</start>
<end>40</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 1-800-SHARED-TASKS at RegNLP: Lexical Reranking of Semantic Retrieval (LeSeR) for Regulatory Question Answering
%A Purbey, Jebish
%A Sharma, Drishti
%A Gupta, Siddhant
%A Murad, Khawaja
%A Pullakhandam, Siddartha
%A Kadiyala, Ram Mohan Rao
%Y Gokhan, Tuba
%Y Wang, Kexin
%Y Gurevych, Iryna
%Y Briscoe, Ted
%S Proceedings of the 1st Regulatory NLP Workshop (RegNLP 2025)
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F purbey-etal-2025-1-800-shared
%X This paper presents the system description of our entry for the COLING 2025 RegNLP RIRAG (Regulatory Information Retrieval and Answer Generation) challenge, focusing on leveraging advanced information retrieval and answer generation techniques in regulatory domains. We experimented with a combination of embedding models, including Stella, BGE, CDE, and Mpnet, and leveraged fine-tuning and reranking for retrieving relevant documents in top ranks. We utilized a novel approach, LeSeR, which achieved competitive results with a recall@10 of 0.8201 and map@10 of 0.6655 for retrievals. This work highlights the transformative potential of natural language processing techniques in regulatory applications, offering insights into their capabilities for implementing a retrieval augmented generation system while identifying areas for future improvement in robustness and domain adaptation.
%U https://aclanthology.org/2025.regnlp-1.6/
%P 36-40
Markdown (Informal)
[1-800-SHARED-TASKS at RegNLP: Lexical Reranking of Semantic Retrieval (LeSeR) for Regulatory Question Answering](https://aclanthology.org/2025.regnlp-1.6/) (Purbey et al., RegNLP 2025)
ACL