Zero-shot learning and out-of-distribution generalization: two sides of the same coin

Add to your list(s) Download to your calendar using vCal

• Jonathan Berant, Tel Aviv University
• Thursday 02 December 2021, 11:00-12:00
• https://cam-ac-uk.zoom.us/j/97599459216?pwd=QTRsOWZCOXRTREVnbTJBdXVpOXFvdz09.

If you have a question about this talk, please contact Haim Dubossarsky.

Recent advances in large pre-trained language models have shifted the NLP community’s attention to new challenges: (a) training models with zero, or very few, examples, and (b) generalizing to out-of-distribution examples. In this talk, I will argue that the two are intimately related, and describe ongoing (read, new!) work in those directions. First, I will describe a new pre-training scheme for open-domain question answering that is based on the notion of “recurring spans” across different paragraphs. We show this training scheme leads to a zero-shot retriever that is competitive with DPR (which trains on thousands of examples), and is more robust w.r.t the test distribution. Second, I will focus on compositional generalization, a particular type of out-of-distribution generalization setup where models need to generalize to structures that are unobserved at training time. I will show that the view that seq2seq models categorically do not generalize to new compositions is false, and present a more nuanced analysis, which elucidates what are the conditions under which models struggle to compositionally generalize.

This talk is part of the Language Technology Lab Seminars series.

This talk is included in these lists:

• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Guy Emerson's list
• Interested Talks
• Language Sciences for Graduate Students
• Language Technology Lab Seminars
• Simon Baker's List
• Trust & Technology Initiative - interesting events
• bld31
• https://cam-ac-uk.zoom.us/j/97599459216?pwd=QTRsOWZCOXRTREVnbTJBdXVpOXFvdz09
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.