Sotabase

Career

· Senior Research Scientist, IBM Research
· Project Scientist, UC San Diego
· Researcher/Research Scientist, UC San Diego

Publications (76)

CORD-19: The Covid-19 Open Research Dataset
NLPCOVID19 · 2020
856
cited
A Survey of the State of Explainable AI for Natural Language Processing
AACL · 2020
439
cited
AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industry
North American Chapter of the Association for Computational Linguistics · 2021
63
cited
Challenges in the construction of knowledge bases for human microbiome-disease associations
Microbiome · 2019
52
cited
NormCo: Deep Disease Normalization for Biomedical Knowledge Base Construction
Conference on Automated Knowledge Base Construction · 2019
52
cited
Video Analysis
Encyclopedia of Database Systems · 2009
43
cited
Complete yet practical search for minimal query reformulations under constraints
SIGMOD Conference · 2014
37
cited
Exploring the Use of Personalized AI for Identifying Misinformation on Social Media
International Conference on Human Factors in Computing Systems · 2023
36
cited
Fact checking and analyzing the web
ACM SIGMOD Conference · 2013
36
cited
mtRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems
Transactions of the Association for Computational Linguistics · 2025
30
cited
View-based Data Integration
Encyclopedia of Database Systems · 2009
28
cited
XNLP: A Living Survey for XAI Research in Natural Language Processing
IUI Companion · 2021
28
cited
Utilizing IDs to Accelerate Incremental View Maintenance
SIGMOD Conference · 2015
24
cited
Exporting and interactively querying Web service-accessed sources: The CLIDE System
TODS · 2007
21
cited
Zero-shot Topical Text Classification with LLMs - an Experimental Study
Conference on Empirical Methods in Natural Language Processing · 2023
21
cited
Combining Databases and Signal Processing in Plato
Conference on Innovative Data Systems Research · 2015
20
cited
Label Sleuth: From Unlabeled Text to a Classifier in a Few Hours
Conference on Empirical Methods in Natural Language Processing · 2022
20
cited
Growing triples on trees: an XML-RDF hybrid model for annotated documents
The VLDB journal · 2011
19
cited
Simplifying Information Integration: Object-Based Flow-of-Mappings Framework for Integration
Business Intelligence for the Real-Time Enterprises · 2008
19
cited
Big Data Techniques for Public Health: A Case Study
IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies · 2017
18
cited
Sotabase