• Publications
  • Influence
Transition-Based Dependency Parsing with Stack Long Short-Term Memory
TLDR
This work was sponsored in part by the U. S. Army Research Laboratory and the European Commission under the contract numbers FP7-ICT-610411 (project MULTISENSOR). Expand
  • 676
  • 86
  • PDF
DyNet: The Dynamic Neural Network Toolkit
TLDR
We describe DyNet, a toolkit for implementing neural network models based on dynamic declaration of network structure. Expand
  • 329
  • 27
  • PDF
XNMT: The eXtensible Neural Machine Translation Toolkit
TLDR
This paper describes XNMT, the eXtensible Neural Machine Translation toolkit, a toolkit that optimizes not for efficiency, but instead for ease of use in practical research settings. Expand
  • 45
  • 3
  • PDF
The CMU Machine Translation Systems at WMT 2013: Syntax, Synthetic Translation Options, and Pseudo-References
TLDR
We describe the CMU systems submitted to the 2013 WMT shared task in machine translation. Expand
  • 18
  • 3
  • PDF
Synthesizing Compound Words for Machine Translation
TLDR
We present a simple and effective approach that deals with this problem in two phases. Expand
  • 9
  • 2
  • PDF
The CMU Machine Translation Systems at WMT 2014
TLDR
We describe the CMU systems submitted to the 2014 WMT shared translation task. Expand
  • 13
  • 1
  • PDF
Using Morphological Knowledge in Open-Vocabulary Neural Language Models
TLDR
We introduce an open-vocabulary language model that incorporates more sophisticated linguistic knowledge by predicting words using a mixture of three generative processes: (1) by generating words as a sequence of characters, (2) by directly generating full word forms, and (3) using a hand-written morphological analyzer. Expand
  • 13
  • PDF
The ARIEL-CMU Systems for LoReHLT18
TLDR
This paper describes the ARIEL-CMU submissions to the Low Resource Human Language Technologies (LoReHLT) 2018 evaluations for the tasks Machine Translation (MT), Entity Discovery and Linking (EDL), and detection of Situation Frames in Text and Speech. Expand
  • 5
  • PDF
Tree Transduction Tools for cdec
TLDR
We describe a collection of open source tools for learning tree-to-string and tree- to-tree transducers and the extensions to the cdec decoder that enable translation with these. Expand
  • 2
  • PDF
Comparing Top-Down and Bottom-Up Neural Generative Dependency Models
TLDR
We introduce and evaluate two new generative models of projective dependency syntax, so as to explore whether generative dependency models are similarly effective. Expand