About
Our lab has been devoted to developing novel NLP methods, software, and applications for diverse biomedical texts, such as clinical notes, biomedical literature, and social media. These three areas complement each other: new methods lead to software that are used by many researchers, software facilitates clinical applications, and successful applications reveal where there is need for new methods, closing the loop and forming an ecosystem of our research activities in clinical NLP.
Methods
Developing novel methods for various challenging clinical NLP topics, such as named entity recognition, word sense disambiguation, syntactic parsing, semantic role labeling, active learning, and now large language models (LLMs).
Software
Building robust clinical NLP software, such as MedEx (Medication Information Extraction System), and CLAMP (Clinical Language Annotation, Modeling, and Processing). The CLAMP tool has been downloaded by over 650 healthcare organizations worldwide, and it has achieved successful commercialization.
Applications
Applying clinical NLP technologies to clinical and translational research and clinical practice. We have collaborated with clinical investigators and successfully conducted many important clinical and translational studies using electronic health records.
Biomedical NLP Challenges
We have participated in many NLP challenges and have achieved top rankings in many of them.
| NLP Challenge Tasks | Ranking | |
|---|---|---|
| Named entity recognition | 2009 i2b2 medication information extraction | #2 |
| 2010 i2b2 problem, treatment, test extraction | #2 | |
| 2013 SHARe/CLEF abbreviation recognition | #1 | |
| 2016 CEGS N-GRID, De-identification | #2 | |
| UMLS encoding | 2014 SemEval, disorder encoding | #1 |
| Relation extraction | 2012 i2b2 Temporal information extraction | #1 |
| 2015 SemEval Disease-modifier extraction | #1 | |
| 2015 BioCREATIVE Chemical-induced disease from literature | #1 | |
| 2016 SemEvel, temporal information extraction | #1 | |
| 2017 TAC ADR extraction from drug labels | #1 | |
| 2018 n2c2, medication and associated ADR | #1 | |
| 2022 LitCoin Challenge on literature mining | #2 | |
Contact us
Have questions or want to learn more about our lab's research and expertise? Please don't hesitate to reach out.
Location:
100 College Street, New Haven, CT 06510
Email:
