35 citations · 142 across the 18 of their papers we have counts for
7 papers · 1 filter
QEMind: Alibaba's Submission to the WMT21 Quality Estimation Shared Task
Jiayi Wang, Ke Wang, Boxing Chen +3
Quality Estimation, as a crucial step of quality control for machine translation, has been explored for years. The goal is to investigate automatic methods for estimating the quali…
KGR^4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generation
Xin Liu, Dayiheng Liu, Baosong Yang +6
Generative commonsense reasoning requires machines to generate sentences describing an everyday scenario given several concepts, which has attracted much attention recently. Howeve…
Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables
Weizhi Wang, Zhirui Zhang, Yichao Du +3
Zero-shot translation, directly translating between language pairs unseen in training, is a promising capability of multilingual neural machine translation (NMT). However, it usual…
Non-Parametric Online Learning from Human Feedback for Neural Machine Translation
Dongqi Wang, Haoran Wei, Zhirui Zhang +3
We study the problem of online learning with human feedback in the human-in-the-loop machine translation, in which the human translators revise the machine-generated translations a…
Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation
Xin Zheng, Zhirui Zhang, Shujian Huang +4
Recently, NN-MT has shown the promising capability of directly incorporating the pre-trained neural machine translation (NMT) model with domain-specific token-level -nearest-…
Task-Oriented Dialogue System as Natural Language Generation
Weizhi Wang, Zhirui Zhang, Junliang Guo +3
In this paper, we propose to formulate the task-oriented dialogue system as the purely natural language generation task, so as to fully leverage the large-scale pre-trained models…
Towards Variable-Length Textual Adversarial Attacks
Junliang Guo, Zhirui Zhang, Linlin Zhang +4
Adversarial attacks have shown the vulnerability of machine learning models, however, it is non-trivial to conduct textual adversarial attacks on natural language processing tasks…