[webMeetup] Can neural networks learn to predict pragmatic inferences?

![[webMeetup] Can neural networks learn to predict pragmatic inferences?](https://secure.meetupstatic.com/photos/event/7/e/2/e/highres_495812302.webp?w=750)
Details
Join the 47th NLP Zurich tech shindig 5th May 2021 online. Sebastian Schuster (NYU) will talk about a pragmatic inference prediction with neural networks. This event is organized together with the Institute of Computation Linguistics at the University of Zurich. We are looking forward to welcoming you.
Agenda
17:55 Join the webMeetup
18:00 Sebastian Schuster (Computing Innovation Fellow): Can neural networks learn to predict pragmatic inferences?
18:35 Q&A
18:50 Virtual Hugs and Kisses ⊂(◉‿◉)つ
Talk summary
Pragmatic inferences often subtly depend on the presence or absence of linguistic features. For example, the presence of a partitive construction (of the) increases the strength of a so-called scalar inference: listeners perceive the inference that Chris did not eat all of the cookies to be stronger after hearing "Chris ate some of the cookies" than after hearing the same utterance without a partitive, "Chris ate some cookies."
In this talk, I will discuss how such scalar inferences vary across contexts, to what extent neural network sentence encoders can learn to predict the strength of these inferences based on two case studies (the inference from "some" to "not all" and the inference from "or" to "not both"), and to what extent the models learn associations between previously established linguistic features and inference strength.
Speaker
Sebastian Schuster is a Computing Innovation Fellow at the Center of Data Science and the Department of Linguistics at NYU. His research focuses on computational models of pragmatic utterance interpretation. He is also a core member of the Universal Dependencies initiative, where he leads efforts to make multilingual dependency representations more useful for natural language understanding tasks. He holds an MS degree in Computer Science and a PhD in Linguistics from Stanford University, and a BS in Computer Science from the University of Vienna.
Twitter: @sebschu Website: http://www.sebschu.com
Organizers
Insititute of Computation Linguistics at the University of Zurich:
NLP Zurich:
Meetup.com: https://www.meetup.com/NLP-Zurich/
Linkedin: https://www.linkedin.com/company/nlp-zurich
Twitter: https://twitter.com/nlp_zurich

[webMeetup] Can neural networks learn to predict pragmatic inferences?