Reut Tsarfaty Profile picture
Associate Professor at Bar-Ilan University * Research Scientist at AI2 #NLProc #AI #compling #deeplearn
Jun 29, 2021 12 tweets 5 min read
Most digital assistants that follow NL instructions focus on uncovering concrete pred-arg structures, such as "book a flight" or "send a mail". However, when humans convey complex instructions they often resort to abstractions, such as emerging shapes, iterations, conditions 1/n Can #nlproc models learn to interpret such abstract structures, and ground them in a concrete world?

We set out to elicit non-trivial natural lang instructions that contain multiple levels of abstraction, and evaluate models ability to execute them.
arxiv.org/abs/2106.14321

2/n
Jun 29, 2021 10 tweets 6 min read
#abstraction in #NLProc: a thread >> According to Wing 2011, #abstraction in natural language is the act of referring to a set of elements via their shared properties, discarding irrelevant distinctions.

It can be a shape they make ("object"), order of traversal ("control structure") or a condition they all meet>>