2021-22 Distinguished Computational Linguistics Lecture

The 2021-22 Distinguished Computational Linguistics Lecture, sponsored by the Language Science program in the College of Liberal Arts, features Professor Marie-Catherine de Marneffe from The Ohio State University. Her talk is titled "Can neural networks identify actuality?".

Abstract: When we communicate, we infer a lot beyond the literal meaning of the words we hear or read. In particular, our understanding of an utterance depends on assessing the extent to which the speaker presents events as factual. An unadorned declarative like “The cancer has spread” conveys firm speaker commitment of the cancer having spread, whereas “There are some indicators that the cancer has spread” imbues the claim with uncertainty. In this talk, I will investigate how well BERT, a current neural language model, performs on predicting factuality in several existing English datasets, encompassing various linguistic constructions. I will show that, although BERT achieves very good results, it does so by exploiting surface patterns that correlate with certain factuality labels, but it fails on items that necessitate pragmatic knowledge. These results highlight directions for improvement to build robust natural language understanding systems.

Register Zoom webinar: https://rit.zoom.us/webinar/register/WN_9mXBC6luRDO6-dz-s3g23g

For more information on Language Science at RIT: https://www.rit.edu/cla/languagescience/