7 citations · 20 across the 5 of their papers we have counts for
5 papers
One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code
Yong Dai, Duyu Tang, Liangxin Liu +7
People perceive the world with multiple senses (e.g., through hearing sounds, reading words and seeing objects). However, most existing AI systems only process an individual modali…
Pretraining Chinese BERT for Detecting Word Insertion and Deletion Errors
Cong Zhou, Yong Dai, Duyu Tang +4
Chinese BERT models achieve remarkable progress in dealing with grammatical errors of word substitution. However, they fail to handle word insertion and deletion because BERT assum…
"Is Whole Word Masking Always Better for Chinese BERT?": Probing on Chinese Grammatical Error Correction
Yong Dai, Linyang Li, Cong Zhou +5
Whole word masking (WWM), which masks all subwords corresponding to a word at once, makes a better English BERT model. For the Chinese language, however, there is no subword becaus…
SkillNet-NLU: A Sparsely Activated Model for General-Purpose Natural Language Understanding
Fan Zhang, Duyu Tang, Yong Dai +3
Prevailing deep models are single-purpose and overspecialize at individual tasks. However, when being extended to new tasks, they typically forget previously learned skills and lea…
Pretraining without Wordpieces: Learning Over a Vocabulary of Millions of Words
Zhangyin Feng, Duyu Tang, Cong Zhou +6
The standard BERT adopts subword-based tokenization, which may break a word into two or more wordpieces (e.g., converting "lossless" to "loss" and "less"). This will bring inconven…