M
Minwei Feng
Researcher at IBM
Publications - 33
Citations - 2154
Minwei Feng is an academic researcher from IBM. The author has contributed to research in topics: Machine translation & Deep learning. The author has an hindex of 11, co-authored 31 publications receiving 1750 citations. Previous affiliations of Minwei Feng include RWTH Aachen University.
Papers
More filters
Posted Content
A Structured Self-attentive Sentence Embedding
Zhouhan Lin,Minwei Feng,Cicero Nogueira dos Santos,Mo Yu,Bing Xiang,Bowen Zhou,Yoshua Bengio +6 more
TL;DR: This paper proposed a self-attention mechanism and a special regularization term for the model, which achieved a significant performance gain compared to other sentence embedding methods in all of the three tasks.
Proceedings Article
A Structured Self-Attentive Sentence Embedding.
Zhouhan Lin,Minwei Feng,Cicero Nogueira dos Santos,Mo Yu,Bing Xiang,Bowen Zhou,Yoshua Bengio +6 more
TL;DR: A new model for extracting an interpretable sentence embedding by introducing self-attention is proposed, which uses a 2-D matrix to represent the embedding, with each row of the matrix attending on a different part of the sentence.
Proceedings ArticleDOI
Applying deep learning to answer selection: A study and an open task
TL;DR: A general deep learning framework is applied to address the non-factoid question answering task and demonstrates superior performance compared to the baseline methods and various technologies give further improvements.
Posted Content
Applying Deep Learning to Answer Selection: A Study and An Open Task
TL;DR: This article applied a general deep learning framework to non-factoid question answering task, which does not rely on any linguistic tools and can be applied to different languages or domains and demonstrate superior performance compared to the baseline methods and various technologies give further improvements.
Proceedings ArticleDOI
Efficient Hyper-parameter Optimization for NLP Applications
TL;DR: This paper proposes a multi-stage hyper-parameter optimization that breaks the problem into multiple stages with increasingly amounts of data, and demonstrates the utility of this new algorithm by evaluating its speed and accuracy against state-of-the-art Bayesian Optimization algorithms on classification and prediction tasks.