Abstract The materials science research process has become increasingly autonomous due to the remarkable progress in artificial intelligence. However, topic selection (ARTS) not yet been fully explored difficulty of estimating its promise and lack previous research. This paper introduces an ARTS system that autonomously selects potential topics are likely reveal new scientific facts have subjec...

In this paper, we propose a framework to produce topic-focused summarization of news events, based on biased snippet extraction and selection. Through our approach, a summarization only retaining information related to a predefined topic (e.g. economy or politics) can be generated for a given news event to satisfy users with specific interests. To better balance coherence and coverage of the su...

We present an open domain topic prediction model for the answer selection task. Different from previous unsupervised topic modeling methods, we automatically extract high quality and large scale 〈sentence, topic〉 pairs from Wikipedia as labeled data, and train an open domain topic prediction model based on convolutional neural network, which can predict the most possible topics for each given i...