Latent Topology Induction for Understanding Contextualized Representations

Yao Fu, Mirella Lapata

TL;DR: We discover the hidden topology within the representation space of contextualized representations

Abstract: Recently, there has been considerable interests in understanding pretrained language models. This work studies the hidden geometry of the representation space of language models from a unique topological perspective. We hypothesize that there exist a network of latent anchor states summarizing the topology (neighbors and connectivity) of the representation space. we infer this latent network in a fully unsupervised way using a structured variational autoencoder. We show that such network exists in pretrained representations, but not in baseline random or positional embeddings. We connect the discovered topological structure to their linguistic interpretations. In this latent network, leave nodes can be grounded to word surface forms, anchor states can be grounded to linguistic categories, and connections between nodes and states can be grounded to phrase constructions and syntactic templates. We further show how such network evolves as the embeddings become more contextualized, with observational and statistical evidence demonstrating how contextualization helps words “receive meaning” from their topological neighbors via the anchor states. We demonstrate these insights with extensive experiments and visualizations.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)