Linguistics Homecoming Lecture

Wednesday, October 4, 2017 @ 4:00 pm, Silsby 312
Natalie Schrimpf, Yale University (Dartmouth '12)
Combining Topic Structure with Rhetorical Information for Automatic Summarization
In this talk, I will give an overview of automatic summarization and present some of my current research, which combines topic structure with rhetorical information to create improved summaries. Summarization involves finding the most important information in a text in order to convey the meaning of the document. In my work, I propose a method for using topic information to influence which content is selected for a summary. Texts are divided into topics using rhetorical information that creates a partition of a text into a sequence of non-overlapping topics. To investigate the effect of this topic structure, I compare the output of summarizing an entire text without topics to summarizing individual topics and combining them into a complete summary. The results show that the use of these rhetorical topics improves summarization performance compared to a summarization system that incorporates no topic information, demonstrating the utility of topic structure and rhetorical information for automatic summarization.

This event is free and open to the public!
Sponsored by the Linguistics Program