Ming-Wei Chang

TL;DR: A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.

TL;DR: BERT as mentioned in this paper pre-trains deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.

TL;DR: The Natural Questions corpus, a question answering data set, is presented, introducing robust metrics for the purposes of evaluating question answering systems; demonstrating high human upper bounds on these metrics; and establishing baseline results using competitive methods drawn from related literature.

TL;DR: This work proposes a novel semantic parsing framework for question answering using a knowledge base that leverages the knowledge base in an early stage to prune the search space and thus simplifies the semantic matching problem.

TL;DR: How SVM, a new learning technique, is successfully applied to load forecasting is discussed in detail and some important conclusions are that temperature might not be useful in such a mid-term load forecasting problem and that the introduction of time-series concept may improve the forecasting.