Bird’s Eye: Probing for Linguistic Graph Structures with a Simple Information-Theoretic Approach

Yifan Hou, Mrinmaya Sachan


Abstract
NLP has a rich history of representing our prior understanding of language in the form of graphs. Recent work on analyzing contextualized text representations has focused on hand-designed probe models to understand how and to what extent do these representations encode a particular linguistic phenomenon. However, due to the inter-dependence of various phenomena and randomness of training probe models, detecting how these representations encode the rich information in these linguistic graphs remains a challenging problem. In this paper, we propose a new information-theoretic probe, Bird’s Eye, which is a fairly simple probe method for detecting if and how these representations encode the information in these linguistic graphs. Instead of using model performance, our probe takes an information-theoretic view of probing and estimates the mutual information between the linguistic graph embedded in a continuous space and the contextualized word representations. Furthermore, we also propose an approach to use our probe to investigate localized linguistic information in the linguistic graphs using perturbation analysis. We call this probing setup Worm’s Eye. Using these probes, we analyze the BERT models on its ability to encode a syntactic and a semantic graph structure, and find that these models encode to some degree both syntactic as well as semantic information; albeit syntactic information to a greater extent.
Anthology ID:
2021.acl-long.145
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1844–1859
Language:
URL:
https://aclanthology.org/2021.acl-long.145
DOI:
10.18653/v1/2021.acl-long.145
Bibkey:
Cite (ACL):
Yifan Hou and Mrinmaya Sachan. 2021. Bird’s Eye: Probing for Linguistic Graph Structures with a Simple Information-Theoretic Approach. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1844–1859, Online. Association for Computational Linguistics.
Cite (Informal):
Bird’s Eye: Probing for Linguistic Graph Structures with a Simple Information-Theoretic Approach (Hou & Sachan, ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.145.pdf
Video:
 https://aclanthology.org/2021.acl-long.145.mp4
Code
 yifan-h/Graph_Probe-Birds_Eye
Data
AMR BankPenn Treebank