Papers by Xavier Amatriain

2 papers
Dr. Summarize: Global Summarization of Medical Dialogue by Exploiting Local Structures. (2020.findings-emnlp)

Copied to clipboard

Challenge: Summarization of medical conversations addresses a very real need in medical practice: capturing the most important aspects of a medical encounter.
Approach: They propose a novel approach to medical conversation summarization that leverages the unique and independent local structures created when gathering a patient’s medical history.
Outcome: The proposed model captures most or all of the information in 80% of the medical conversations making it a realistic alternative to costly manual summarization by medical experts.
Injecting knowledge into language generation: a case study in auto-charting after-visit care instructions from medical dialogue (2023.acl-long)

Copied to clipboard

Challenge: Recent advances in language modeling have enabled applications across multiple domains such as education, jurisprudence, and healthcare.
Approach: They propose a method to use knowledge to identify which rare words are important and uplift their conditional probability.
Outcome: The proposed approach reduces the uncertainty of the model and improves factuality and coherence without negatively impacting fluency.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations