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
Enabling Search and Collaborative Assembly of Causal Interactions Extracted from Multilingual and Multi-domain Free Text
George Caique Gouveia Barbosa,Zechy Wong,Gus Hahn-Powell,Dane Bell,Rebecca Sharp,Marco Antonio Valenzuela-Escárcega,Mihai Surdeanu +6 more
TL;DR: A system that incorporates multi-domain extractions of causal interactions into a single searchable knowledge graph enables users to search iteratively over direct and indirect connections in this knowledge graph, and collaboratively build causal models in real time.
Proceedings Article
Automatic Correction of Syntactic Dependency Annotation Differences
TL;DR: A method for automatically detecting annotation mismatches between dependency parsing corpora, along with three related methods for automatically converting the mismatches, and finds that applying these conversions yields significantly better performance in many cases.
Proceedings ArticleDOI
Taxonomy Builder: a Data-driven and User-centric Tool for Streamlining Taxonomy Construction
John P Hungerford,Yee Seng Chan,J. MacBride,Benjamin M. Gyori,Andrew Lee Zupon,Zheng Tang,Egoitz Laparra,Haoling Qiu,Bonan Min,Yan Zverev,Caitlin Hilverman,M. Thomas,Walt Andrews,Keith Alcock,Zeyu Zhang,Michael Reynolds,Mihai Surdeanu,Steven Bethard,Rebecca Emilie Sharp +18 more
TL;DR: Insight from text summarization and information extraction is applied to reduce the search space dramatically, then modern pretrained language models are leveraged to perform contextualized clustering of the remaining concepts to yield candidate nodes for the user to review.
Journal ArticleDOI
Learning Open Domain Multi-hop Search Using Reinforcement Learning
TL;DR: The method learns a policy for directing existing information retrieval and machine reading resources to focus on relevant regions of a corpus and finds a family of policies that succeeds in extracting the desired information while processing fewer documents compared to several baseline heuristic algorithms.
Proceedings ArticleDOI
Low Resource Causal Event Detection from Biomedical Literature
TL;DR: This paper shows that, by using very limited amount of labeled data, and sufficient amount of unlabeled data, the neural models outperform previous baselines on the causal precedence detection task, and are ten times faster at inference compared to the BERT base model.