Ziang Xie

Neural Text Generation: A Practical Guide

2017 · arXiv (Cornell University)

Deep learning methods have recently achieved great empirical success on machine translation, dialogue response generation, summarization, and other text generation tasks. At a high level, the technique has been to train end-to-end neural network models …

Lexicon-Free Conversational Speech Recognition with Neural Networks

2015

We present an approach to speech recognition that uses only a neural network to map acoustic input to characters, a character-level language model, and a beam search decoding procedure. This approach eliminates much of the …

Data Noising as Smoothing in Neural Network Language Models

2017 · arXiv (Cornell University)

Data noising is an effective technique for regularizing neural network models. While noising is widely adopted in application domains such as vision and speech, commonly used noising primitives have not been developed for discrete sequence-level …

Noising and Denoising Natural Language: Diverse Backtranslation for Grammar Correction

2018

Ziang Xie, Guillaume Genthial, Stanley Xie, Andrew Ng, Dan Jurafsky. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.