N
Nan Yang
Researcher at Microsoft
Publications - 17
Citations - 2358
Nan Yang is an academic researcher from Microsoft. The author has contributed to research in topics: Context (language use) & Artificial neural network. The author has an hindex of 12, co-authored 17 publications receiving 1919 citations.
Papers
More filters
Proceedings ArticleDOI
Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification
TL;DR: Three neural networks are developed to effectively incorporate the supervision from sentiment polarity of text (e.g. sentences or tweets) in their loss functions and the performance of SSWE is improved by concatenating SSWE with existing feature set.
Journal ArticleDOI
Sentiment Embeddings with Applications to Sentiment Analysis
TL;DR: This work develops a number of neural networks with tailoring loss functions, and applies sentiment embeddings to word-level sentiment analysis, sentence level sentiment classification, and building sentiment lexicons, showing results that consistently outperform context-basedembeddings on several benchmark datasets of these tasks.
Proceedings Article
Modeling mention, context and entity with neural networks for entity disambiguation
TL;DR: A new neural network approach is presented that takes consideration of the semantic representations of mention, context and entity, encodes them in continuous vector space and effectively leverages them for entity disambiguation.
Proceedings Article
Pseudo-Masked Language Models for Unified Language Model Pre-Training
Hangbo Bao,Li Dong,Furu Wei,Wenhui Wang,Nan Yang,Xiaodong Liu,Yu Wang,Jianfeng Gao,Songhao Piao,Ming Zhou,Hsiao-Wuen Hon +10 more
TL;DR: The experiments show that the unified language models pre-trained using PMLM achieve new state-of-the-art results on a wide range of natural language understanding and generation tasks across several widely used benchmarks.
Proceedings ArticleDOI
A Recursive Recurrent Neural Network for Statistical Machine Translation
TL;DR: A novel recursive recurrent neural network (R 2 NN) is proposed to model the end-to-end decoding process for statistical machine translation and can outperform the state of theart baseline by about 1.5 points in BLEU.