@inproceedings{winter-etal-2024-ddxgym-online,
title = "{DD}x{G}ym: Online Transformer Policies in a Knowledge Graph Based Natural Language Environment",
author = "Winter, Benjamin and
Figueroa Rosero, Alexei Gustavo and
Loeser, Alexander and
Gers, Felix Alexander and
Figueroa Rosero, Nancy Katerina and
Krestel, Ralf",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.396",
pages = "4438--4448",
abstract = "Differential diagnosis (DDx) is vital for physicians and challenging due to the existence of numerous diseases and their complex symptoms. Model training for this task is generally hindered by limited data access due to privacy concerns. To address this, we present DDxGym, a specialized OpenAI Gym environment for clinical differential diagnosis. DDxGym formulates DDx as a natural-language-based reinforcement learning (RL) problem, where agents emulate medical professionals, selecting examinations and treatments for patients with randomly sampled diseases. This RL environment utilizes data labeled from online resources, evaluated by medical professionals for accuracy. Transformers, while effective for encoding text in DDxGym, are unstable in online RL. For that reason we propose a novel training method using an auxiliary masked language modeling objective for policy optimization, resulting in model stabilization and significant performance improvement over strong baselines. Following this approach, our agent effectively navigates large action spaces and identifies universally applicable actions. All data, environment details, and implementation, including experiment reproduction code, are made publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="winter-etal-2024-ddxgym-online">
<titleInfo>
<title>DDxGym: Online Transformer Policies in a Knowledge Graph Based Natural Language Environment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Winter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexei</namePart>
<namePart type="given">Gustavo</namePart>
<namePart type="family">Figueroa Rosero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Loeser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="given">Alexander</namePart>
<namePart type="family">Gers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="given">Katerina</namePart>
<namePart type="family">Figueroa Rosero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ralf</namePart>
<namePart type="family">Krestel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Differential diagnosis (DDx) is vital for physicians and challenging due to the existence of numerous diseases and their complex symptoms. Model training for this task is generally hindered by limited data access due to privacy concerns. To address this, we present DDxGym, a specialized OpenAI Gym environment for clinical differential diagnosis. DDxGym formulates DDx as a natural-language-based reinforcement learning (RL) problem, where agents emulate medical professionals, selecting examinations and treatments for patients with randomly sampled diseases. This RL environment utilizes data labeled from online resources, evaluated by medical professionals for accuracy. Transformers, while effective for encoding text in DDxGym, are unstable in online RL. For that reason we propose a novel training method using an auxiliary masked language modeling objective for policy optimization, resulting in model stabilization and significant performance improvement over strong baselines. Following this approach, our agent effectively navigates large action spaces and identifies universally applicable actions. All data, environment details, and implementation, including experiment reproduction code, are made publicly available.</abstract>
<identifier type="citekey">winter-etal-2024-ddxgym-online</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.396</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4438</start>
<end>4448</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DDxGym: Online Transformer Policies in a Knowledge Graph Based Natural Language Environment
%A Winter, Benjamin
%A Figueroa Rosero, Alexei Gustavo
%A Loeser, Alexander
%A Gers, Felix Alexander
%A Figueroa Rosero, Nancy Katerina
%A Krestel, Ralf
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F winter-etal-2024-ddxgym-online
%X Differential diagnosis (DDx) is vital for physicians and challenging due to the existence of numerous diseases and their complex symptoms. Model training for this task is generally hindered by limited data access due to privacy concerns. To address this, we present DDxGym, a specialized OpenAI Gym environment for clinical differential diagnosis. DDxGym formulates DDx as a natural-language-based reinforcement learning (RL) problem, where agents emulate medical professionals, selecting examinations and treatments for patients with randomly sampled diseases. This RL environment utilizes data labeled from online resources, evaluated by medical professionals for accuracy. Transformers, while effective for encoding text in DDxGym, are unstable in online RL. For that reason we propose a novel training method using an auxiliary masked language modeling objective for policy optimization, resulting in model stabilization and significant performance improvement over strong baselines. Following this approach, our agent effectively navigates large action spaces and identifies universally applicable actions. All data, environment details, and implementation, including experiment reproduction code, are made publicly available.
%U https://aclanthology.org/2024.lrec-main.396
%P 4438-4448
Markdown (Informal)
[DDxGym: Online Transformer Policies in a Knowledge Graph Based Natural Language Environment](https://aclanthology.org/2024.lrec-main.396) (Winter et al., LREC-COLING 2024)
ACL