[Adapt] Improving Truthfulness of Headline Generation

[陈浩平]

Hi Adapters,
    Most studies on abstractive summarization report ROUGE scores between system and reference summaries. However, we have a concern about the truthfulness of generated summaries:
whether all facts of a generated summary are mentioned in the source text. My talk today will introduce a paper that analyses the task and dataset on two popular headline generation datasets and explores ways to improve the truthfulness of them. 





Time: Wed 4:00pm

Venue: SEIEE 3-414

Best,
Apple
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20211027/bb7dae77/attachment.htm>