Probing with Noise: Unpicking the Warp and Weft of Embeddings

Filip Klubicka, John Kelleher


Abstract
Improving our understanding of how information is encoded in vector space can yield valuable interpretability insights. Alongside vector dimensions, we argue that it is possible for the vector norm to also carry linguistic information. We develop a method to test this: an extension of the probing framework which allows for relative intrinsic interpretations of probing results. It relies on introducing noise that ablates information encoded in embeddings, grounded in random baselines and confidence intervals. We apply the method to well-established probing tasks and find evidence that confirms the existence of separate information containers in English GloVe and BERT embeddings. Our correlation analysis aligns with the experimental findings that different encoders use the norm to encode different kinds of information: GloVe stores syntactic and sentence length information in the vector norm, while BERT uses it to encode contextual incongruity.
Anthology ID:
2022.blackboxnlp-1.34
Volume:
Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates (Hybrid)
Editors:
Jasmijn Bastings, Yonatan Belinkov, Yanai Elazar, Dieuwke Hupkes, Naomi Saphra, Sarah Wiegreffe
Venue:
BlackboxNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
404–417
Language:
URL:
https://aclanthology.org/2022.blackboxnlp-1.34
DOI:
10.18653/v1/2022.blackboxnlp-1.34
Bibkey:
Cite (ACL):
Filip Klubicka and John Kelleher. 2022. Probing with Noise: Unpicking the Warp and Weft of Embeddings. In Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pages 404–417, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
Cite (Informal):
Probing with Noise: Unpicking the Warp and Weft of Embeddings (Klubicka & Kelleher, BlackboxNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.blackboxnlp-1.34.pdf
Video:
 https://aclanthology.org/2022.blackboxnlp-1.34.mp4