We propose a unified model combining the strength of extractive and abstractive summarization. On the one hand, a simple extractive model can obtain sentence-level attention with high ROUGE scores but less readable. On the other hand, a more complicated abstractive model can obtain word-level dynamic attention to generate a more readable paragraph. In our model, sentence-level attention is used to modulate the word-level attention such that words in less attended sentences are less likely to be generated. Moreover, a novel inconsistency loss function is introduced to penalize the inconsistency between two levels of attentions. By end-to-end training our model with the inconsistency loss and original losses of extractive and abstractive models, we achieve state-of-theart ROUGE scores while being the most informative and readable summarization on the CNN/Daily Mail dataset in a solid human evaluation.
We present SYNC, a crowdsourcing platform that allows news audiences to read news curated, aggregated, organized, and edited by the crowd, and to participate in news aggregation and editing at anytime. Through crowdsourcing, SYNC brings together news information from diverse sources and from contributors with different perspectives, enabling news audiences to obtain a more complete context of specific news events, thereby synchronizing their knowledge of the event. SYNC employs "blocks" and a timeline to help with editors structure and organize news information, and a news material panel to facilitate finding news material to help with aggregation and editing. Our user evaluation showed that participants were positive about the usefulness and societal impacts of SYNC, and found the user interface easy to follow. They also indicated improvements to make to better support news aggregation and editing.
CCS CONCEPTS• Human-centered computing → Collaborative and social computing.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.