526 citations · 1.2k across the 26 of their papers we have counts for
3 papers · 1 filter
Sparse Overcomplete Word Vector Representations
Manaal Faruqui, Yulia Tsvetkov, Dani Yogatama +2
Current distributed representations of words show little resemblance to theories of lexical semantics. The former are dense and uninterpretable, the latter largely based on familia…
Transition-Based Dependency Parsing with Stack Long Short-Term Memory
Chris Dyer, Miguel Ballesteros, Wang Ling +2
We propose a technique for learning representations of parser states in transition-based dependency parsers. Our primary innovation is a new control structure for sequence-to-seque…
Bayesian Optimization of Text Representations
Dani Yogatama, Noah A. Smith
When applying machine learning to problems in NLP, there are many choices to make about how to represent input texts. These choices can have a big effect on performance, but they a…