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
A STEP towards Interpretable Multi-Hop Reasoning:Bridge Phrase Identification and Query Expansion
Fan Luo,Mihai Surdeanu +1 more
TL;DR: An unsupervised method for the identification of bridge phrases in multi-hop question answering (QA) that constructs a graph of noun phrases from the question and the available context and applies the Steiner tree algorithm to identify the minimal sub-graph that connects all question phrases.
Posted Content
How May I Help You? Using Neural Text Simplification to Improve Downstream NLP Tasks
TL;DR: The authors investigated the use of text simplification for NLP tasks and showed that simplifying input texts at prediction time and augmenting data to provide machines with additional information during training can improve NLP performance.
Posted Content
Learning what to read: Focused machine reading
TL;DR: The authors introduce 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 demonstrate that the RL approach is capable of answering more queries than the baseline, while being more efficient than reading fewer documents.
Proceedings Article
Informal Persian Universal Dependency Treebank
TL;DR: The phonological, morphological, and syntactic distinctions between formal and informal Persian are presented, showing that these two variants have fundamental differences that cannot be attributed solely to pronunciation discrepancies.
Proceedings Article
Bootstrapping Neural Relation and Explanation Classifiers
Zheng Tang,Mihai Surdeanu +1 more
TL;DR: This article self-trained a relation classifier with an explanation classifier that identifies context words important for the relation at hand, iteratively converting the explainable models' outputs to rules and applying them to unlabeled text to produce new annotations.