@inproceedings{minh-etal-2025-dragon,
title = "{DRAGON}: Dual-Encoder Retrieval with Guided Ontology Reasoning for Medical Normalization",
author = "Minh, Dao Sy Duy and
Quy, Nguyen Lam Phu and
Hoa, Pham Phu and
Nguyen, Tran Chi and
Kiet, Huynh Trung and
Tran, Truong Bao",
editor = "Kummerfeld, Jonathan K. and
Joshi, Aditya and
Dras, Mark",
booktitle = "Proceedings of the 23rd Annual Workshop of the Australasian Language Technology Association",
month = nov,
year = "2025",
address = "Sydney, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.alta-main.18/",
pages = "230--239",
ISBN = "1834-7037",
abstract = "Adverse Drug Event (ADE) normalization to standardized medical terminologies such as MedDRA presents significant challenges due to lexical and semantic gaps between colloquial user-generated content and formal medical vocabularies. This paper presents our submission to the ALTA 2025 Shared Task on ADE normalization, evaluated using Accuracy@k metrics. Our approach employs distinct methodologies for the development and test phase. In the development phase, we propose a three-stage neural architecture: (1) bi-encoder training to establish semantic representations, (2) lexical-aware fine-tuning to capture morphological patterns alongside semantic similarity, and (3) crossencoder re-ranking for fine-grained discrimination, enabling the model to leverage both distributional semantics and lexical cues through explicit interaction modeling. For the test phase, we utilize the trained bi-encoder from stage (1) for efficient candidate retrieval, then adopt an alternative re-ranking pipeline leveraging large language models with tool-augmented retrieval and multi-stage reasoning. Specifically, a capable model performs reasoning-guided candidate selection over the retrieved top-k results, a lightweight model provides iterative feedback based on reasoning traces, and an automated verification module ensures output correctness with self-correction mechanisms. Our system achieves competitive performance on both development and test benchmarks, demonstrating the efficacy of neural retrieval-reranking architectures and the versatility of LLM-augmented neural pipelines for medical entity normalization tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="minh-etal-2025-dragon">
<titleInfo>
<title>DRAGON: Dual-Encoder Retrieval with Guided Ontology Reasoning for Medical Normalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dao</namePart>
<namePart type="given">Sy</namePart>
<namePart type="given">Duy</namePart>
<namePart type="family">Minh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nguyen</namePart>
<namePart type="given">Lam</namePart>
<namePart type="given">Phu</namePart>
<namePart type="family">Quy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pham</namePart>
<namePart type="given">Phu</namePart>
<namePart type="family">Hoa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tran</namePart>
<namePart type="given">Chi</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huynh</namePart>
<namePart type="given">Trung</namePart>
<namePart type="family">Kiet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Truong</namePart>
<namePart type="given">Bao</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Annual Workshop of the Australasian Language Technology Association</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Kummerfeld</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Dras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Sydney, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">1834-7037</identifier>
</relatedItem>
<abstract>Adverse Drug Event (ADE) normalization to standardized medical terminologies such as MedDRA presents significant challenges due to lexical and semantic gaps between colloquial user-generated content and formal medical vocabularies. This paper presents our submission to the ALTA 2025 Shared Task on ADE normalization, evaluated using Accuracy@k metrics. Our approach employs distinct methodologies for the development and test phase. In the development phase, we propose a three-stage neural architecture: (1) bi-encoder training to establish semantic representations, (2) lexical-aware fine-tuning to capture morphological patterns alongside semantic similarity, and (3) crossencoder re-ranking for fine-grained discrimination, enabling the model to leverage both distributional semantics and lexical cues through explicit interaction modeling. For the test phase, we utilize the trained bi-encoder from stage (1) for efficient candidate retrieval, then adopt an alternative re-ranking pipeline leveraging large language models with tool-augmented retrieval and multi-stage reasoning. Specifically, a capable model performs reasoning-guided candidate selection over the retrieved top-k results, a lightweight model provides iterative feedback based on reasoning traces, and an automated verification module ensures output correctness with self-correction mechanisms. Our system achieves competitive performance on both development and test benchmarks, demonstrating the efficacy of neural retrieval-reranking architectures and the versatility of LLM-augmented neural pipelines for medical entity normalization tasks.</abstract>
<identifier type="citekey">minh-etal-2025-dragon</identifier>
<location>
<url>https://aclanthology.org/2025.alta-main.18/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>230</start>
<end>239</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DRAGON: Dual-Encoder Retrieval with Guided Ontology Reasoning for Medical Normalization
%A Minh, Dao Sy Duy
%A Quy, Nguyen Lam Phu
%A Hoa, Pham Phu
%A Nguyen, Tran Chi
%A Kiet, Huynh Trung
%A Tran, Truong Bao
%Y Kummerfeld, Jonathan K.
%Y Joshi, Aditya
%Y Dras, Mark
%S Proceedings of the 23rd Annual Workshop of the Australasian Language Technology Association
%D 2025
%8 November
%I Association for Computational Linguistics
%C Sydney, Australia
%@ 1834-7037
%F minh-etal-2025-dragon
%X Adverse Drug Event (ADE) normalization to standardized medical terminologies such as MedDRA presents significant challenges due to lexical and semantic gaps between colloquial user-generated content and formal medical vocabularies. This paper presents our submission to the ALTA 2025 Shared Task on ADE normalization, evaluated using Accuracy@k metrics. Our approach employs distinct methodologies for the development and test phase. In the development phase, we propose a three-stage neural architecture: (1) bi-encoder training to establish semantic representations, (2) lexical-aware fine-tuning to capture morphological patterns alongside semantic similarity, and (3) crossencoder re-ranking for fine-grained discrimination, enabling the model to leverage both distributional semantics and lexical cues through explicit interaction modeling. For the test phase, we utilize the trained bi-encoder from stage (1) for efficient candidate retrieval, then adopt an alternative re-ranking pipeline leveraging large language models with tool-augmented retrieval and multi-stage reasoning. Specifically, a capable model performs reasoning-guided candidate selection over the retrieved top-k results, a lightweight model provides iterative feedback based on reasoning traces, and an automated verification module ensures output correctness with self-correction mechanisms. Our system achieves competitive performance on both development and test benchmarks, demonstrating the efficacy of neural retrieval-reranking architectures and the versatility of LLM-augmented neural pipelines for medical entity normalization tasks.
%U https://aclanthology.org/2025.alta-main.18/
%P 230-239
Markdown (Informal)
[DRAGON: Dual-Encoder Retrieval with Guided Ontology Reasoning for Medical Normalization](https://aclanthology.org/2025.alta-main.18/) (Minh et al., ALTA 2025)
ACL