2.2k citations · 5k across the 31 of their papers we have counts for
3 papers · 1 filter
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
Dario Amodei, Rishita Anubhai, Eric Battenberg +31
We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech--two vastly different languages. Because it replaces entire pip…
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…
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…