1.8k citations · 2.1k across the 6 of their papers we have counts for
5 papers · 1 filter
Towards Using Context-Dependent Symbols in CTC Without State-Tying Decision Trees
Jan Chorowski, Adrian Lancucki, Bartosz Kostka +1
Deep neural acoustic models benefit from context-dependent (CD) modeling of output symbols. We consider direct training of CTC networks with CD outputs, and identify two issues. Th…
Efficient Purely Convolutional Text Encoding
Szymon Malik, Adrian Lancucki, Jan Chorowski
In this work, we focus on a lightweight convolutional architecture that creates fixed-size vector embeddings of sentences. Such representations are useful for building NLP systems,…
A Talker Ensemble: the University of Wrocław's Entry to the NIPS 2017 Conversational Intelligence Challenge
Jan Chorowski, Adrian Łańcucki, Szymon Malik +3
We present Poetwannabe, a chatbot submitted by the University of Wrocław to the NIPS 2017 Conversational Intelligence Challenge, in which it ranked first ex-aequo. It is able to co…
On Multilingual Training of Neural Dependency Parsers
Michał Zapotoczny, Paweł Rychlikowski, Jan Chorowski
We show that a recently proposed neural dependency parser can be improved by joint training on multiple languages from the same family. The parser is implemented as a deep neural n…
Attention-Based Models for Speech Recognition
Jan Chorowski, Dzmitry Bahdanau, Dmitriy Serdyuk +2
Recurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks in- cluding machine translation…