Our model is a simple feed-forward neural network that operates on a task-specific transition system, yet achieves comparable or better accuracies than recurrent models.
Ranked #8 on Dependency Parsing on Penn Treebank
Neural machine translation (NMT) models typically operate with a fixed vocabulary, but translation is an open-vocabulary problem.
Ranked #1 on Machine Translation on WMT2015 English-Russian
State-of-the-art sequence labeling systems traditionally require large amounts of task-specific knowledge in the form of hand-crafted features and data pre-processing.
Ranked #9 on Part-Of-Speech Tagging on Penn Treebank
In this paper, we propose LexVec, a new method for generating distributed word representations that uses low-rank, weighted factorization of the Positive Point-wise Mutual Information matrix via stochastic gradient descent, employing a weighting scheme that assigns heavier penalties for errors on frequent co-occurrences while still accounting for negative co-occurrence.
Understanding how words change their meanings over time is key to models of language and cultural evolution, but historical data on meaning is scarce, making theories hard to develop and test.
CopyNet can nicely integrate the regular way of word generation in the decoder with the new copying mechanism which can choose sub-sequences in the input sequence and put them at proper places in the output sequence.
Enabling a computer to understand a document so that it can answer comprehension questions is a central, yet unsolved goal of NLP.
Ranked #3 on Question Answering on CNN / Daily Mail