activity
20162026
most citedTransfer Learning for Sequence Tagging with Hierarchical Recurrent Networks

218 citations · 381 across the 26 of their papers we have counts for

collaborators
Showing 2017 · cs.CLShow all

5 papers · 2 filters

cs.CL2017

Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent

Zhilin Yang, Saizheng Zhang, Jack Urbanek +5

Contrary to most natural language processing research, which makes use of static datasets, humans learn language interactively, grounded in an environment. In this work we propose…

cs.CL2017

Breaking the Softmax Bottleneck: A High-Rank RNN Language Model

Zhilin Yang, Zihang Dai, Ruslan Salakhutdinov +1

We formulate language modeling as a matrix factorization problem, and show that the expressiveness of Softmax-based models (including the majority of neural language models) is lim…

cs.CL2017★ 218 cited

Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks

Zhilin Yang, Ruslan Salakhutdinov, William W. Cohen

Recent papers have shown that neural networks obtain state-of-the-art performance on several different sequence tagging tasks. One appealing property of such systems is their gener…

cs.CL2017★ 33 cited

Linguistic Knowledge as Memory for Recurrent Neural Networks

Bhuwan Dhingra, Zhilin Yang, William W. Cohen +1

Training recurrent neural networks to model long term dependencies is difficult. Hence, we propose to use external linguistic knowledge as an explicit signal to inform the model wh…

cs.CL2017

Semi-Supervised QA with Generative Domain-Adaptive Nets

Zhilin Yang, Junjie Hu, Ruslan Salakhutdinov +1

We study the problem of semi-supervised question answering----utilizing unlabeled text to boost the performance of question answering models. We propose a novel training framework,…