513 citations · 1.4k across the 15 of their papers we have counts for
3 papers · 1 filter
Ontology-Aware Token Embeddings for Prepositional Phrase Attachment
Pradeep Dasigi, Waleed Ammar, Chris Dyer +1
Type-level word embeddings use the same set of parameters to represent all instances of a word regardless of its context, ignoring the inherent lexical ambiguity in language. Inste…
Semi-supervised sequence tagging with bidirectional language models
Matthew E. Peters, Waleed Ammar, Chandra Bhagavatula +1
Pre-trained word embeddings learned from unlabeled text have become a standard component of neural network architectures for NLP tasks. However, in most cases, the recurrent networ…
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…