Dimitri Coelho Mollo and Raphaël Millière: The Vector Grounding Problem
Wed
25
May
Wednesday 25 May, 2022at 13:15 - 15:00
HD108
The Research Seminar Series in Philosophy invites you to a seminar with Dimitri Coelho Mollo (Umeå University) and Raphaël Millière (Columbia University). Research paper, "The Vector Grounding Problem".
Abstract: The impressive performance of current artificial language models in complex linguistic tasks has generated considerable debate about how to understand their abilities. Are their surprisingly compelling linguistic outputs just mere statistical parroting of the huge trove of text they were trained on, lacking grounding in the real world, and thus devoid of intrinsic meaning, unable to be about the world?
In this paper, our aim is two-fold. First, we will distinguish different senses of representational grounding: referential, sensorimotor, communicative, and epistemic. We will argue that the referential sense of grounding is the central one for assessing whether language models are more than mere stochastic parrots. Second, we will argue that, in light of their architecture and training, artificial language models could satisfy the minimal conditions for the relevant notion of representational grounding. Language models are typically trained on datasets whose implicit structure essentially depends on causal interactions between humans and the world, and have to learn to represent and exploit such structure to produce their outputs. We will show that our best theories of representational content can make space for representational grounding in language models, and even more so in visuo-linguistic models.
All interested are welcome to participate in this seminar.