Aman Sinha | Université de Lorraine

About Me

I am a PhD student at Université de Lorraine, Nancy, France, under the supervision of Marianne Clausel, Mathieu Constant and Xavier Coubez. My research involves exploring the structure of data in medical domain to enhance Natural Language Processing based models. Most recently, I’m interested in 1) exploiting temporal characterstics of medical data to create better outcome prediction models, and 2) integrating knowledge graphs to complement medical decision support systems.

Research Interests

Medical Language Understanding
Natural Language Processing

News

[Sep. 2024] Will attend Athens NLP 2024 Summer School in Athens, Greece.
[Aug. 2024] 2 workshop papers accepted at ACL 2024.
[Jul. 2024] Visting Researcher at University of Helsinki, Finland.
[Nov. 2023] Will be attending LIFT 2023 held at LORIA, Nancy, France.
[Nov. 2023] Will be presenting a poster on "Can LLMs be used to understand clinical notes better?" at LIFT 2023.
[Sept. 2023] Attended Tools in Causality Summer School held at Autrans, Grenoble, France.
[Sept. 2023] Attended CCAIM Summer school.
[July 2023] Attended ESSAI & ACAI Summer school (virtually).
[Apr. 2023] Gave a talk "Understanding Medical Language - A deep learning perspective" at PariSanté Campus, Paris, France.
[Feb. 2023] Visited Simula Research Laboratory, Oslo, Norway.
[Feb. 2023] Attended AAAI 2023 (virtually).

Relevant Publications

2024

BioNLP 2024

Domain-specific or Uncertainty-aware models: Does it really make a difference for biomedical text classification?

Aman Sinha, Timothee Mickus, Marianne Clausel, Mathieu Constant, and Xavier Coubez

In Proceedings of the 23rd Workshop on Biomedical Natural Language Processing, pages 202–211, Bangkok, Thailand. Association for Computational Linguistics. Aug 2024.

PDF

KnowledgeLM 2024

Retrieve, Generate, Evaluate: A Case Study for Medical Paraphrases Generation with Small Language Models

Ioana Buhnila, Aman Sinha, and Mathieu Constant

In Proceedings of the 1st Workshop on Towards Knowledgeable Language Models (KnowLLM 2024), pages 189–203, Bangkok, Thailand. Association for Computational Linguistics. Aug 2024.

PDF Code

2023

ArXiv

Modelling Irregularly Sampled Time Series Without Imputation

Rohit Agarwal ,Aman Sinha, Dilip Prasad, Marianne Clausel, Alexander Horsh, Mathieu Constant, and Xavier Coubez

ArXiv 2309.08698. Sept 2023.

PDF

ARTS 2023

What shall we read: the article or the citations?-A case study on scientific language understanding

Aman Sinha, Sam Bigeard, Marianne Clausel, and Mathieu Constant

Actes de CORIA-TALN 2023. Actes de l’atelier" Analyse et Recherche de Textes Scientifiques"(ARTS), TALN-CORIA 2023.

PDF

2022

WNLPe-Health 2022

CME² Net: Contextual Medical Event Extraction Network for clinical notes

Aman Sinha, Ayan Vishwakarma, Marianne Clausel, and Mathieu Constant

Proceedings of the 19th International Conference on Natural Language Processing: Workshop on Context-aware NLP in eHealth (WNLPe-Health), ICON 2022.

PDF Code

SMM4H 2022

IAI@ SocialDisNER: Catch me if you can! Capturing complex disease mentions in tweets

Aman Sinha, Cristina García Holgado, Marianne Clausel, and Mathieu Constant

Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task (SMM4H), COLING 2022.

PDF Code

[Complete list: Google Scholar]