M
Mihai Surdeanu
Researcher at University of Arizona
Publications - 188
Citations - 15228
Mihai Surdeanu is an academic researcher from University of Arizona. The author has contributed to research in topics: Question answering & Computer science. The author has an hindex of 39, co-authored 163 publications receiving 13691 citations. Previous affiliations of Mihai Surdeanu include Pompeu Fabra University & Polytechnic University of Catalonia.
Papers
More filters
Proceedings ArticleDOI
Cache-aware load balancing for question answering
TL;DR: This paper investigates the load balancing problem proposing two novel algorithms that take into account the distributed cache status, in addition to the CPU and I/O load in each processing node, and demonstrates the choice of using the status of the cache was determinant in achieving good performance, and high throughput for QA systems.
Patent
Systems and Methods for Using Non-Textual Information In Analyzing Patent Matters
Mihai Surdeanu,Ingrid Kaldre Foster,Carla L. Rydholm,Ramesh Nallapati,Joshua H. Walker,George D. Gregory,Gavin Carothers,Nicholas O. Pilon +7 more
TL;DR: In this article, a non-textual information in analyses of patent matters is used to measure the similarity between patent portfolio patents and patent matters at issue, and a metric that measures the textual similarity between the textual description and patent patent matters.
Patent
Systems and Methods for Classifying Entities
TL;DR: In this paper, the authors present systems and method for generating and/or using a classifier that can identify or classify entities, such as whether an entity in a contested proceeding is a patent monetizing entity (PME).
Journal ArticleDOI
Science Citation Knowledge Extractor
Heather C. Lent,Gustave Hahn-Powell,Asher Haug-Baltzell,Sean Davey,Mihai Surdeanu,Eric Lyons +5 more
TL;DR: The Science Citation Knowledge Extractor (SCKE), a web tool to provide biological and biomedical researchers with an overview of how their work is being utilized by the broader scientific community, and present users with interactive data visualizations which illustrate how their works are contributing to greater scientific pursuits.
Posted Content
SnapToGrid: From Statistical to Interpretable Models for Biomedical Information Extraction
TL;DR: The results show that there is a small performance penalty when converting the statistical model to rules, but the gain in interpretability compensates for that: with minimal effort, human experts improve this model to have similar performance to the statisticalmodel that served as starting point.