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
Infrastructure for open-domain information extraction
TL;DR: In this paper, the CICERO system combines the role of linguistic patterns with coreference knowledge and ambiguous syntactic and semantic information to perform open-domain information extraction (IE).
Book ChapterDOI
Language Technologies: Question Answering in Speech Transcripts
TL;DR: This simple example illustrates the two main advantages of QA over current search engines: first, the input is a natural-language question rather a keyword query; and second, the answer provides the desired information content and not simply a potentially large set of documents or URLs that the user must plow through.
Proceedings Article
Automatic Discovery of Linguistic Patterns for Information Extraction
TL;DR: CICERO is implemented in CICERO, the IE system, a pattern acquisition mechanism that combines lexicosemantic knowledge available from WordNet with syntactic information collected from training corpora that grants portability of the approach across multiple extraction domains.
Proceedings ArticleDOI
A mostly unlexicalized model for recognizing textual entailment
TL;DR: This paper proposes a model that reads two sentences, from any given domain, to determine entailment without using lexicalized features, which relies on features that are either unlexicalized or are domain independent such as proportion of negated verbs, antonyms, or noun overlap.
Proceedings ArticleDOI
Learning what to read: Focused machine reading
TL;DR: This work introduces a focused reading approach to guide the machine reading of biomedical literature towards what literature should be read to answer a biomedical query as efficiently as possible and demonstrates that the RL approach is capable of answering more queries than the baseline, while being more efficient, i.e., reading fewer documents.