We validate CoNT on five generation tasks with ten benchmarks, including machine translation, summarization, code comment generation, data-to-text generation and commonsense generation.
There is a growing interest in dataset generation recently due to the superior generative capacity of large pre-trained language models (PLMs).
LogiRE treats logic rules as latent variables and consists of two modules: a rule generator and a relation extractor.
Ranked #18 on Relation Extraction on DocRED
This paper describes the Volctrans' submission to the WMT21 news translation shared task for German->English translation.
Developing a unified multilingual model has long been a pursuit for machine translation.
The key idea is that at each time step, the network takes as input a ``bundle'' of similar words predicted at the previous step instead of a single ground truth.
We investigate the following question for machine translation (MT): can we develop a single universal MT model to serve as the common seed and obtain derivative and improved models on arbitrary language pairs?
Ranked #3 on Machine Translation on WMT2014 English-French (using extra training data)
We propose adversarial uncertainty sampling in discrete space (AUSDS) to retrieve informative unlabeled samples more efficiently.
Non-autoregressive models are promising on various text generation tasks.
Commanding a robot to navigate with natural language instructions is a long-term goal for grounded language understanding and robotics.
However, position modeling of output words is an essential problem in non-autoregressive text generation.
We also design an efficient dynamic programming algorithm to decode segments that allows the model to be trained faster than the existing neural phrase-based machine translation method by Huang et al. (2018).