B
Bing Bai
Researcher at Princeton University
Publications - 43
Citations - 1312
Bing Bai is an academic researcher from Princeton University. The author has contributed to research in topics: Search engine indexing & Ranking (information retrieval). The author has an hindex of 17, co-authored 38 publications receiving 1211 citations. Previous affiliations of Bing Bai include Carnegie Mellon University & Rutgers University.
Papers
More filters
Proceedings ArticleDOI
Sentiment classification based on supervised latent n-gram analysis
TL;DR: A deep neural network is utilized to build a unified discriminative framework that allows for estimating the parameters of the latent space as well as the classification function with a bias for the target classification task at hand.
Patent
Systems and methods for semi-supervised relationship extraction
TL;DR: In this paper, a convolutional and semi-supervised approach for relation extraction in text is described. But it is not shown how to identify the relational pattern of interest in the text in response to a query.
Journal ArticleDOI
Learning to rank with (a lot of) word features
Bing Bai,Jason Weston,David Grangier,Ronan Collobert,Kunihiko Sadamasa,Yanjun Qi,Olivier Chapelle,Kilian Q. Weinberger +7 more
TL;DR: This article defines a class of nonlinear (quadratic) models that are discriminatively trained to directly map from the word content in a query-document or document-document pair to a ranking score.
Proceedings ArticleDOI
Supervised semantic indexing
Bing Bai,Jason Weston,David Grangier,Ronan Collobert,Kunihiko Sadamasa,Yanjun Qi,Olivier Chapelle,Kilian Q. Weinberger +7 more
TL;DR: This article proposes Supervised Semantic Indexing (SSI), an algorithm that is trained on (query, document) pairs of text documents to predict the quality of their match and proposes several improvements to the basic model, including low rank (but diagonal preserving) representations, and correlated feature hashing (CFH).
Journal ArticleDOI
Hierarchical Tracking by Reinforcement Learning-Based Searching and Coarse-to-Fine Verifying
TL;DR: This work proposes a hierarchical tracker that learns to move and track based on the combination of data-driven search at the coarse level and coarse-to-fine verification at the fine level, and utilizes a recurrent convolutional neural network-based deep Q-network to effectively learn data- driven searching policies.