343 citations · 1.7k across the 69 of their papers we have counts for
5 papers · 1 filter
End-to-End Neural Segmental Models for Speech Recognition
Hao Tang, Liang Lu, Lingpeng Kong +5
Segmental models are an alternative to frame-based models for sequence prediction, where hypothesized path weights are based on entire segment scores rather than a single frame at…
SyntaxNet Models for the CoNLL 2017 Shared Task
Chris Alberti, Daniel Andor, Ivan Bogatyy +10
We describe a baseline dependency parsing system for the CoNLL2017 Shared Task. This system, which we call "ParseySaurus," uses the DRAGNN framework [Kong et al, 2017] to combine t…
DRAGNN: A Transition-based Framework for Dynamically Connected Neural Networks
Lingpeng Kong, Chris Alberti, Daniel Andor +2
In this work, we present a compact, modular framework for constructing novel recurrent neural architectures. Our basic module is a new generic unit, the Transition Based Recurrent…
Multitask Learning with CTC and Segmental CRF for Speech Recognition
Liang Lu, Lingpeng Kong, Chris Dyer +1
Segmental conditional random fields (SCRFs) and connectionist temporal classification (CTC) are two sequence labeling methods used for end-to-end training of speech recognition mod…
DyNet: The Dynamic Neural Network Toolkit
Graham Neubig, Chris Dyer, Yoav Goldberg +22
We describe DyNet, a toolkit for implementing neural network models based on dynamic declaration of network structure. In the static declaration strategy that is used in toolkits l…