PI Ndapa Nakashole‘s group applies Machine Learning to problems in Natural Language Processing (NLP). We develop language technologies for a variety of problem domains: healthcare, through the lenses of entity linking, question answering, conversational agents, and multimodal summarization; natural language interfaces, to support accessibility to real world systems to allow more people to access functionality behind APIs, and databases without requiring knowledge of programming languages; and machine translation with a particular interest in low resource languages.
Selected publications
- A Grounded Well-being Conversational Agent with Multiple Interaction Modes: Preliminary Results, NLP4PI at ACL 2021
- A Gradually Soft Multi-Task and Data-Augmented Approach to Medical Question Understanding, ACL 2021
- ChartDialogs: Plotting from Natural Language Instructions, code dataset, ACL 2020
- Characterizing Departures from Linearity in Word Translation, ACL 2018
- Knowledge Distillation for Bilingual Dictionary Induction, EMNLP 2017
- Never-Ending Learning, AAAI 2015
Language-Aware Truth Assessment of Fact Candidates, ACL 2014 - Fine-grained Semantic Typing of Emerging Entities, ACL 2013
- PATTY: A Taxonomy of Relational Patterns with Semantic Types, EMNLP 2012
sds
csssaf
We thank the following sponsors for supporting our research:
