Mihai Surdeanu

Biographic Data

ID6536235
NAMEMihai Surdeanu
GIVEN NAMESMihai
FAMILY NAMESurdeanu
SIGNATURESURDEANU M
AFFILIATIONSUniversity of Arizona
ORCID0000-0001-6956-8030
VERIFIEDYes
TOTAL WORKS6
TOTAL CITATIONS7
AUTHOR COUNT6
EDITOR COUNT0
FIRST PUBLICATION YEAR2011
LATEST PUBLICATION YEAR2022
H-INDEX2

  • It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers

    Open AccessZheng Tang, Mihai SurdeanuARTICLEComputational Linguistics2022References: 1

    We propose an explainable approach for relation extraction that mitigates the tension between generalization and explainability by jointly training for the two goals. Our approach uses a multi-task learning architecture, which jointly trains a classifier for relation extraction, and a sequence model that labels words in the context of the relations that explain the decisions of the relation classifier. We also convert the model outputs to rules t…

  • Framing QA as Building and Ranking Intersentence Answer Justifications

    Open AccessPeter Jansen, Rebecca Sharp et al.ARTICLEComputational Linguistics2017References: 2

    We propose a question answering (QA) approach for standardized science exams that both identifies correct answers and produces compelling human-readable justifications for why those answers are correct. Our method first identifies the actual information needed in a question using psycholinguistic concreteness norms, then uses this information need to construct answer justifications by aggregating multiple sentences from different knowledge bases …

  • The Stanford CoreNLP Natural Language Processing Toolkit

    Open AccessChristopher D Manning, Christopher Manning et al.CONFERENCEProceedings of 52nd Annual…2014

    Christopher Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven Bethard, David McClosky. Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations. 2014.

  • Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules

    Open AccessHeeyoung Lee, Angel Chang et al.ARTICLEComputational Linguistics2013Cited by: 3References: 6

    We propose a new deterministic approach to coreference resolution that combines the global information and precise features of modern machine-learning models with the transparency and modularity of deterministic, rule-based systems. Our sieve architecture applies a battery of deterministic coreference models one at a time from highest to lowest precision, where each model builds on the previous model's cluster output. The two stages of our sieve-…

  • Selectional Preferences for Semantic Role Classification

    Open AccessBeñat Zapirain, Eneko Agirre et al.ARTICLEComputational Linguistics2012Cited by: 2References: 5

    This paper focuses on a well-known open issue in Semantic Role Classification (SRC) research: the limited influence and sparseness of lexical features. We mitigate this problem using models that integrate automatically learned selectional preferences (SP). We explore a range of models based on WordNet and distributional-similarity SPs. Furthermore, we demonstrate that the SRC task is better modeled by SP models centered on both verbs and preposit…

  • Learning to Rank Answers to Non-Factoid Questions from Web Collections

    Open AccessMihai Surdeanu, Massimiliano Ciaramita et al.ARTICLEComputational Linguistics2011Cited by: 2References: 2

    This work investigates the use of linguistically motivated features to improve search, in particular for ranking answers to non-factoid questions. We show that it is possible to exploit existing large collections of question–answer pairs (from online social Question Answering sites) to extract such features and train ranking models which combine them effectively. We investigate a wide range of feature types, some exploiting natural language proce…