Y
Yuan Zhang
Researcher at Massachusetts Institute of Technology
Publications - 23
Citations - 1003
Yuan Zhang is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Parsing & Dependency grammar. The author has an hindex of 15, co-authored 23 publications receiving 929 citations. Previous affiliations of Yuan Zhang include Tsinghua University.
Papers
More filters
Proceedings ArticleDOI
Ten pairs to tag - Multilingual POS tagging via coarse mapping between embeddings
TL;DR: It is demonstrated that accurate multilingual partof-speech (POS) tagging can be done with just a few (e.g., ten) word translation pairs, and the generated tags are used to predict typological properties of languages, obtaining a 50% error reduction relative to the prototype model.
Proceedings ArticleDOI
Low-Rank Tensors for Scoring Dependency Structures
TL;DR: This paper uses tensors to map high-dimensional feature vectors into low dimensional representations of words in their syntactic roles, and to leverage modularity in the tensor for easy training with online algorithms.
Journal ArticleDOI
Aspect-augmented Adversarial Networks for Domain Adaptation
TL;DR: A neural method for transfer learning between two (source and target) classification tasks or aspects over the same domain is introduced, using a few keywords pertaining to source and target aspects indicating sentence relevance instead of document class labels.
Journal ArticleDOI
Quantitative Study of Individual Emotional States in Social Networks
TL;DR: This paper proposes an approach referred to as MoodCast to learn to infer individuals' emotional states and investigates how this person's emotional state influences (or is influenced by) her friends in the social network and verifies the effectiveness of the proposed approach.
Proceedings ArticleDOI
Stack-propagation: Improved Representation Learning for Syntax
Yuan Zhang,David J. Weiss +1 more
TL;DR: This paper proposed a stack-propagation approach for dependency parsing and tagging, where the hidden layer of the tagger network is used as a representation of the input tokens for the parser.