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
Proceedings Article
To Link or Not to Link? A Study on End-to-End Tweet Entity Linking
TL;DR: A structural SVM algorithm for entity linking is proposed that jointly optimizes mention detection and entity disambiguation as a single end-to-end task and is able to outperform existing state-of-the art entity linking systems by 15% F1.
Posted Content
Well-Read Students Learn Better: The Impact of Student Initialization on Knowledge Distillation
TL;DR: It is observed that applying language model pre-training to students unlocks their generalization potential, surprisingly even for very compact networks.
Posted Content
Latent Retrieval for Weakly Supervised Open Domain Question Answering
TL;DR: It is shown for the first time that it is possible to jointly learn the retriever and reader from question-answer string pairs and without any IR system, and outperforming BM25 by up to 19 points in exact match.
Journal ArticleDOI
Structured learning with constrained conditional models
TL;DR: This paper presents Constrained Conditional Models (CCMs), a framework that augments linear models with declarative constraints as a way to support decisions in an expressive output space while maintaining modularity and tractability of training and proposes CoDL, a constraint-driven learning algorithm, which makes use of constraints to guide semi-supervised learning.
Proceedings ArticleDOI
S-MART: Novel Tree-based Structured Learning Algorithms Applied to Tweet Entity Linking
Yi Yang,Ming-Wei Chang +1 more
TL;DR: S-MART, a tree-based structured learning framework based on multiple additive regression trees, is proposed, especially suitable for handling tasks with dense features, and can be used to learn many different structures under various loss functions.