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
Journal Article
Overview of the TAC2013 Knowledge Base Population Evaluation: English Slot Filling and Temporal Slot Filling.
TL;DR: The main changes this year include the requirement for a stricter textual justification of the extracted relations for SF, and a simplification of the TSF task, where the relation to be temporally grounded is given as input.
Proceedings ArticleDOI
Two Practical Rhetorical Structure Theory Parsers
TL;DR: This work describes the design, development, and API for two discourse parsers for Rhetorical Structure Theory, and accompanies this code with a visualization library that runs the two parsers in parallel, and displays the two generated discourse trees side by side, which provides an intuitive way of comparing the two Parsers.
Proceedings ArticleDOI
The Role of Lexico-Semantic Feedback in Open-Domain Textual Question-Answering
Sanda M. Harabagiu,Dan Moldovan,Marius Pasca,Rada Mihalcea,Mihai Surdeanu,Razvan Bunsecu,Roxana Girju,Vasile Rus,Paul Morarescu +8 more
TL;DR: An open-domain textual Question-Answering system that uses several feedback loops to enhance its performance that combines in a new way statistical results with syntactic, semantic or pragmatic information derived from texts and lexical databases is presented.
Proceedings Article
Answering complex, list and context questions with LCC's Question-Answering Server
Sanda M. Harabagiu,Dan Moldovan,Marius Pasca,Mihai Surdeanu,Rada Mihalcea,Corina R. Gîrju,Vasile Rus,Finley Lacatusu,Paul Morarescu,Razvan Bunescu +9 more
TL;DR: The architecture of the Question-Answering server (QAS) developed at the Language Computer Corporation (LCC) and used in the TREC-10 evaluations is presented.
Journal ArticleDOI
Combination strategies for semantic role labeling
TL;DR: This paper introduces and analyzes a battery of inference models for the problem of semantic role labeling: one based on constraint satisfaction, and several strategies that model the inference as a meta-learning problem using discriminative classifiers.