Data Science Talk

Vassilis Tsotras (organizer)

Multidisciplinary Research Building (MRB) Seminar Room,

Sponsored by the Data Science Center, the purpose of the Data Science Seminar is to foster collaborations between the core Data Science faculty (CSE/ECE/STAT) and faculty from other sciences that face Data Science problems in their research. After the talk, there will be time for discussions.The talk will be given by Prof. Yue Dong, Department of Computer Science and Engineering, UCRTITLE:Are hallucinations in text generation always undesirable? A perspective from text elaborationABSTRACT:Recent developments in deep learning have led to exponential improvements in Natural Language Generation (NLG), particularly in terms of fluency and coherency. On the other hand, deep learning-based text generation is also susceptible to hallucinating unintended text that is not directly supported by the source document. These unsupported texts are called hallucinations and are often perceived as undesirable. In this talk, we investigate whether hallucinations are always undesirable through the lens of text summarization and simplification. Surprisingly, we show that many of these unsupported generations provide background knowledge for comprehension. In fact, although the primary tool for summarization and the implication is content reduction, content addition (aka elaborative generation) may also be beneficial for many real-world applications. *** Pizza and refreshments will be provided! ***

Our {communityGuidelinesLink} describe the sort of content we prohibit on Eventbrite. If you suspect an event may be in violation, you can report it to us so we can investigate.

To report other categories of prohibited or illegal content, submit {link}

Data Science Talk

More events from Vassilis Tsotras (organizer)

Follow organizers to get events picked for you

Data Science Talk

More events from Vassilis Tsotras (organizer)

Follow organizers to get events picked for you

You might also like...

Sign-In for personalized recommendations