N
Nan Yang
Researcher at Microsoft
Publications - 35
Citations - 4777
Nan Yang is an academic researcher from Microsoft. The author has contributed to research in topics: Automatic summarization & Sentence. The author has an hindex of 22, co-authored 27 publications receiving 3368 citations. Previous affiliations of Nan Yang include University of Science and Technology of China.
Papers
More filters
Proceedings Article
Unified Language Model Pre-training for Natural Language Understanding and Generation
Li Dong,Nan Yang,Wenhui Wang,Furu Wei,Xiaodong Liu,Yu Wang,Jianfeng Gao,Ming Zhou,Hsiao-Wuen Hon +8 more
TL;DR: UniLM as mentioned in this paper is a unified pre-trained language model that can be fine-tuned for both natural language understanding and generation tasks, achieving state-of-the-art results on five natural language generation datasets, including improving the CNN/DailyMail abstractive summarization ROUGE-L to 40.51 (2.04 absolute improvement).
Proceedings ArticleDOI
Gated Self-Matching Networks for Reading Comprehension and Question Answering
TL;DR: The gated self-matching networks for reading comprehension style question answering, which aims to answer questions from a given passage, are presented and holds the first place on the SQuAD leaderboard for both single and ensemble model.
Posted Content
Unified Language Model Pre-training for Natural Language Understanding and Generation
Li Dong,Nan Yang,Wenhui Wang,Furu Wei,Xiaodong Liu,Yu Wang,Jianfeng Gao,Ming Zhou,Hsiao-Wuen Hon +8 more
TL;DR: A new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks that compares favorably with BERT on the GLUE benchmark, and the SQuAD 2.0 and CoQA question answering tasks.
Proceedings Article
MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers
TL;DR: The authors distill the self-attention module of the last Transformer layer of the teacher, which is effective and flexible for the student, and introduce the scaled dot-product between values in the selfatt attention module as the new deep selfattention knowledge, in addition to the attention distributions.
Book ChapterDOI
Neural Question Generation from Text: A Preliminary Study
TL;DR: A preliminary study on neural question generation from text with the SQuAD dataset is conducted, and the experiment results show that the method can produce fluent and diverse questions.