M
Ming-Wei Chang
Researcher at Google
Publications - 107
Citations - 65337
Ming-Wei Chang is an academic researcher from Google. The author has contributed to research in topics: Question answering & Parsing. The author has an hindex of 41, co-authored 98 publications receiving 36404 citations. Previous affiliations of Ming-Wei Chang include Microsoft & National Taiwan University.
Papers
More filters
Journal ArticleDOI
Sandwich-structured electrospun pH-responsive dental pastes for anti-caries
TL;DR: In this paper , a sandwich-structured electrospun pH-responsive dental paste was engineered via the layer-by-layer electrospinning technique, where the top and bottom layers of the dental paste were pH-sensitive layers prepared with Methylmethacrylate polymers IV (E100), and the middle layer was the polylactic acid (PLA) membrane loading with sodium fluorides (NaF).
Constraint-driven transliteration discovery
TL;DR: A novel constraint-driven learning framework for identifying named-entity (NE) transliterations by considering the aligned segments as a latent feature representation and showing how to infer an optimal latent representation and how to learn an improved discriminative transliteration classifier.
Posted Content
Improving Span-based Question Answering Systems with Coarsely Labeled Data.
TL;DR: This work studies approaches to improve fine-grained short answer Question Answering models by integrating coarse- grained data annotated for paragraph-level relevance and shows that coarsely annotated data can bring significant performance gains.
Posted Content
Joint Passage Ranking for Diverse Multi-Answer Retrieval
TL;DR: The authors propose a joint passage retrieval model focusing on re-ranking, which makes use of an autoregressive re-ranker that selects a sequence of passages, equipped with novel training and decoding algorithms.
Proceedings ArticleDOI
Segmentation based stereo matching using color grouping
TL;DR: This work presents Segmentation based Stereo Matching Using Color Grouping, a meta-analysis of segmentation based stereo matching using color grouping at SIGGRAPH 2014, which aims to provide real-time information about the dynamic response of the human eye.