F
Fei Huang
Researcher at Temple University
Publications - 8
Citations - 323
Fei Huang is an academic researcher from Temple University. The author has contributed to research in topics: Language model & Graphical model. The author has an hindex of 8, co-authored 8 publications receiving 315 citations.
Papers
More filters
Proceedings ArticleDOI
Distributional Representations for Handling Sparsity in Supervised Sequence-Labeling
Fei Huang,Alexander Yates +1 more
TL;DR: It is demonstrated that distributional representations of word types, trained on unannotated text, can be used to improve performance on rare words and reduces the sample complexity of sequence labeling.
Journal ArticleDOI
Learning representations for weakly supervised natural language processing tasks
TL;DR: Novel techniques for extracting features from n-gram models, Hidden Markov Models, and other statistical language models are investigated, including a novel Partial Lattice Markov Random Field model.
Exploring Representation-Learning Approaches to Domain Adaptation
Fei Huang,Alexander Yates +1 more
TL;DR: This work investigates unsupervised techniques for representation learning that provide new features which are stable across domains, in that they are predictive in both the training and out-of-domain test data.
Proceedings Article
Extracting Action and Event Semantics from Web Text
TL;DR: A novel system, PREPOST, is described that tackles the problem of extracting the preconditions and effects of actions and events, two important kinds of knowledge for connecting world state and the actions that affect it.
Proceedings Article
Open-Domain Semantic Role Labeling by Modeling Word Spans
Fei Huang,Alexander Yates +1 more
TL;DR: This work investigates techniques for building open-domain semantic role labeling systems that approach the ideal of a train-once, use-anywhere system and reduces error by 16% relative to the previous state of the art on out-of-domain text.