147 citations · 247 across the 5 of their papers we have counts for
5 papers
SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection
Xiaoya Li, Yuxian Meng, Mingxin Zhou +3
While the self-attention mechanism has been widely used in a wide variety of tasks, it has the unfortunate property of a quadratic cost with respect to the input length, which make…
Dice Loss for Data-imbalanced NLP Tasks
Xiaoya Li, Xiaofei Sun, Yuxian Meng +4
Many NLP tasks such as tagging and machine reading comprehension are faced with the severe data imbalance issue: negative examples significantly outnumber positive examples, and th…
A Unified MRC Framework for Named Entity Recognition
Xiaoya Li, Jingrong Feng, Yuxian Meng +4
The task of named entity recognition (NER) is normally divided into nested NER and flat NER depending on whether named entities are nested or not. Models are usually separately dev…
DSReg: Using Distant Supervision as a Regularizer
Yuxian Meng, Muyu Li, Xiaoya Li +2
In this paper, we aim at tackling a general issue in NLP tasks where some of the negative examples are highly similar to the positive examples, i.e., hard-negative examples. We pro…
Glyce: Glyph-vectors for Chinese Character Representations
Yuxian Meng, Wei Wu, Fei Wang +8
It is intuitive that NLP tasks for logographic languages like Chinese should benefit from the use of the glyph information in those languages. However, due to the lack of rich pict…