08/12/2020

CxGBERT: BERT meets Construction Grammar

Harish Tayyar Madabushi, Laurence Romain, Dagmar Divjak, Petar Milin

Keywords:

Abstract Paper Similar Papers

Abstract: While lexico-semantic elements no doubt capture a large amount of linguistic information, it has been argued that they do not capture all information contained in text. This assumption is central to constructionist approaches to language which argue that language consists of constructions, learned pairings of a form and a function or meaning that are either frequent or have a meaning that cannot be predicted from its component parts. BERT’s training objectives give it access to a tremendous amount of lexico-semantic information, and while BERTology has shown that BERT captures certain important linguistic dimensions, there have been no studies exploring the extent to which BERT might have access to constructional information. In this work we design several probes and conduct extensive experiments to answer this question. Our results allow us to conclude that BERT does indeed have access to a significant amount of information, much of which linguists typically call constructional information. The impact of this observation is potentially far-reaching as it provides insights into what deep learning methods learn from text, while also showing that information contained in constructions is redundantly encoded in lexico-semantics.

The video of this talk cannot be embedded. You can watch it here:
https://underline.io/lecture/6225-cxgbert-bert-meets-construction-grammar
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at COLING 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 7:02 
 0
 0
 0
 0
 11:06 
 0
 0
 0
 0
 15:37 
 0
 0
 0
 0
 12:39 
 0
 0
 0
 0
 12:23 
 0
 0
 0
 0
 4:47 
 0
 0
 0
 0
 13:17 
 0
 0
 0
 0
 9:11 
 0
 0
 0
 0
 11:50 
 0
 0
 0
 0
 4:42 
 0
 0
 0
 0
 11:57 
 0
 0
 0
 0
 10:01 
 0
 0
 0
 0
 6:38 
 0
 0
 0
 0
 14:06 
 0
 0
 0
 0
 14:33 
 0
 0
 0
 0
 12:27 
 0
 0
 0
 0
 10:16 
 0
 0
 0
 0
 6:14 
 0
 0
 0
 0
 12:45 
 0
 0
 0
 0
 4:31 
 0
 0
 0
 0
 11:44 
 0
 0
 0
 0
 12:22 
 0
 0
 0
 0
 18:55 
 0
 0
 0
 0
 15:15 
 0
 0
 0
 0
 10:15 
 0
 0
 0
 0
 10:51 
 0
 0
 0
 0
 13:01 
 0
 0
 0
 0
 11:00 
 0
 0
 0
 0
 2:48 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 5:21 
 0
 0
 0
 0
 11:36 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 6:59 
 0
 0
 0
 0
 11:09 
 0
 0
 0
 0
 9:52 
 0
 0
 0
 0
 7:18 
 0
 0
 0
 0
 7:46 
 0
 0
 0
 0
 12:15 
 0
 0
 0
 0
 14:47