CP’s Talk -Grounded Multi-Agent Language Games

January 10, 2020   งานสัมมนา/ประชุมวิชาการ, ทั่วไป
Grounded Multi-Agent Language Games
I will talk about recent work done at FAIR on novel directions for natural language processing research. While a lot of progress has recently been made in natural language understanding, e.g. by using (contextualized) word and sentence embeddings, big challenges remain. I will discuss fresh perspectives on natural language learning, in the shape of grounded multi-agent language games: While Wittgenstein is often invoked as the godfather of the distributional hypothesis, I argue that he has rather different lessons to teach us. This leads to a new research program for natural language understanding, centering around active language usage in “grounded multi-agent language games”. I will give some examples of research we have done at FAIR that goes in that direction, including our recent work on Adversarial NLI, which proposes a new human-and-model-in-the-loop benchmark for measuring progress in AI.

Douwe Kiela is a research scientist at Facebook AI Research (FAIR). He received his PhD and MPhil from the University of Cambridge Computer Laboratory. Before that, Douwe completed an undergraduate degree in Liberal Arts & Sciences at Utrecht University with a double major in Cognitive Artificial Intelligence and Philosophy; and then a master’s degree in Logic at the University of Amsterdam’s Institute for Logic, Language & Computation. Douwe’s work focuses on machine learning and natural language processing, where his research interests lie in grounded language learning, emergent communication and developing better models for language understanding

Register >>> Click Here