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 Article
Odin’s Runes: A Rule Language for Information Extraction
TL;DR: Odin is an information extraction framework that applies cascades of finite state automata over both surface text and syntactic dependency graphs, and Odin’s declarative language for writing these cascaded automata is described.
Journal ArticleDOI
Combining joint models for biomedical event extraction
TL;DR: A state-of-the-art event extraction system that relies on the strengths of structured prediction and model combination through stacking is presented and outperforms intersection and union and leads to very strong results.
Journal ArticleDOI
Performance analysis of a distributed question/answering system
TL;DR: This paper proposes a distributed Q/A architecture that enhances the system throughput through the exploitation of interquestion parallelism and dynamic load balancing and reduces the individual question response time through the exploit of intraquestion Parallelism.
Proceedings ArticleDOI
Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering
TL;DR: This article proposed an unsupervised strategy for the selection of justification sentences for multi-hop question answering (QA) that maximizes the relevance of the selected sentences, minimizes the overlap between the selected facts, and maximises the coverage of both question and answer.
Proceedings ArticleDOI
Performance analysis of a distributed question/answering system
TL;DR: This paper presents the design and performance analysis of a distributed state-of-the-art Q/A system that is modular and parallelism is dynamically exploited at inter and intra-question levels.