activity
20152026
most citedDistilling Task-Specific Knowledge from BERT into Simple Neural Networks

335 citations · 565 across the 45 of their papers we have counts for

collaborators
Showing 2018Show all

6 papers · 1 filter

cs.CL2018

CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling

Ning Miao, Hao Zhou, Lili Mou +2

In real-world applications of natural language generation, there are often constraints on the target sentences in addition to fluency and naturalness requirements. Existing languag…

cs.LG2018

A Grammar-Based Structural CNN Decoder for Code Generation

Zeyu Sun, Qihao Zhu, Lili Mou +3

Code generation maps a program description to executable source code in a programming language. Existing approaches mainly rely on a recurrent neural network (RNN) as the decoder.…

cs.CL2018

Progressive Memory Banks for Incremental Domain Adaptation

Nabiha Asghar, Lili Mou, Kira A. Selby +3

This paper addresses the problem of incremental domain adaptation (IDA) in natural language processing (NLP). We assume each domain comes one after another, and that we could only…

cs.CL2018

Disentangled Representation Learning for Non-Parallel Text Style Transfer

Vineet John, Lili Mou, Hareesh Bahuleyan +1

This paper tackles the problem of disentangling the latent variables of style and content in language models. We propose a simple yet effective approach, which incorporates auxilia…

cs.IR2018

JUMPER: Learning When to Make Classification Decisions in Reading

Xianggen Liu, Lili Mou, Haotian Cui +2

In early years, text classification is typically accomplished by feature-based machine learning models; recently, deep neural networks, as a powerful learning machine, make it poss…

cs.CL2018

Stochastic Wasserstein Autoencoder for Probabilistic Sentence Generation

Hareesh Bahuleyan, Lili Mou, Hao Zhou +1

The variational autoencoder (VAE) imposes a probabilistic distribution (typically Gaussian) on the latent space and penalizes the Kullback--Leibler (KL) divergence between the post…