Y
Yubin Ge
Researcher at University of Illinois at Urbana–Champaign
Publications - 37
Citations - 512
Yubin Ge is an academic researcher from University of Illinois at Urbana–Champaign. The author has contributed to research in topics: Computer science & Context (language use). The author has an hindex of 11, co-authored 31 publications receiving 300 citations. Previous affiliations of Yubin Ge include University of Rochester & University of Pittsburgh.
Papers
More filters
Proceedings ArticleDOI
Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis.
TL;DR: Recently, this paper proposed a progressive self-supervised attention learning approach for aspect-level sentiment classification, which automatically mines useful attention supervision information from a training corpus to refine attention mechanisms.
Proceedings ArticleDOI
Structural Information Preserving for Graph-to-Text Generation
TL;DR: This work introduces two types of autoencoding losses, each individually focusing on different aspects (a.k.a. views) of input graphs, that can guide the model for preserving input information via multi-task training.
Posted Content
Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models
TL;DR: This paper proposes a novel framework --- deep verifier networks (DVN) to verify the inputs and outputs of deep discriminative models with deep generative models based on conditional variational auto-encoders with disentanglement constraints.
Proceedings ArticleDOI
Dynamic Context-guided Capsule Network for Multimodal Machine Translation
TL;DR: This paper proposes a novel Dynamic Context-guided Capsule Network (DCCN) for MMT, which represents the input image with global and regional visual features, and introduces two parallel DCCNs to model multimodal context vectors with visual features at different granularities.
Journal ArticleDOI
Adaptive metric learning with deep neural networks for video-based facial expression recognition
TL;DR: This work proposes the adaptive (N+M)-tuplet clusters loss function and optimize it with the softmax loss simultaneously in the training phrase to reduce the variation introduced by personal attributes in video-based facial expression recognition.