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
Do Transformers Dream of Inference, or Can Pretrained Generative Models Learn Implicit Inferential Rules?
Zhengzhong Liang,Mihai Surdeanu +1 more
TL;DR: This work investigates the capability of a state-of-the-art transformer LM to generate explicit inference hops, i.e., to infer a new statement necessary to answer a question given some premise input statements.
Proceedings ArticleDOI
An Unsupervised Method for Learning Representations of Multi-word Expressions for Semantic Classification.
TL;DR: With pre-defined MWE boundaries, this method outperforms the previous state-of-the-art performance on the coarse-grained evaluation of the Tratz dataset, with an F1 score of 50.4%.
Proceedings ArticleDOI
MLStar: Machine Learning in Energy Profile Estimation of Android Apps
TL;DR: This paper presents a novel machine learning approach to estimate app energy efficiency by utilizing textual information available in the Google Play store such as an app's description, user reviews, as well as system permissions, and shows that hardware permissions, app description, and user reviews correlate well with energy efficiency ratings.
Proceedings Article
Students Who Study Together Learn Better: On the Importance of Collective Knowledge Distillation for Domain Transfer in Fact Verification
TL;DR: The authors propose Group Learning, a knowledge and model distillation approach for fact verification in which multiple student models have access to different delexicalized views of the data, but are encouraged to learn from each other through pair-wise consistency losses.
Journal ArticleDOI
It is not Sexually Suggestive, It is Educative. Separating Sex Education from Suggestive Content on TikTok Videos
TL;DR: The SexTok dataset as mentioned in this paper is a multi-modal dataset composed of TikTok videos labeled as sexually suggestive (from the annotator's point of view), sex-educational content, or neither.