[1906.02715] Visualizing and Measuring the Geometry of BERT

Transformer architectures show significant promise for natural language processing. Given that a single pretrained model can be fine-tuned to perform well on many different tasks, these networks appear to extract generally useful linguistic features. A natural question is how such networks represent this information internally. This paper describes qualitative and quantitative investigations of one particularly effective model, BERT. At a high level, linguistic features seem to be represented in separate semantic and syntactic subspaces. We find evidence of a fine-grained geometric representation of word senses. We also present empirical descriptions of syntactic representations in both attention matrices and individual word embeddings, as well as a mathematical argument to explain the geometry of these representations.

8 mentions: @wattenberg@viegasf@keigohtr@societyoftrees@dtsbourg@wzuidema@yousui_t_ken@innatok
Keywords: bert
Date: 2019/06/09 03:48

Referring Tweets

@wattenberg How does a neural net represent language? See the visualizations and geometry in this PAIR team paper https://t.co/55GO5lJtsl and blog post https://t.co/jsjwY4Dl4y https://t.co/ZkG81UBHcE
@viegasf Analyzing and visualizing syntax trees in the high-dimensional spaces of neural nets. Check out the new PAIR paper on BERT geometry https://t.co/SPryH5mqnB And the blog post on “Language, trees, and geometry in neural networks” https://t.co/6hMthb5QNL https://t.co/NhTYvhb8aV
@keigohtr ニューラルネットがどう自然言語を理解しているか https://t.co/PY83eZSi0n

Related Entries

Read more GitHub - soskek/bert-chainer: Chainer implementation of "BERT: Pre-training of Deep Bidirectional Tr...
Read more [DL Hacks]BERT: Pre-training of Deep Bidirectional Transformers for L…
Read more [DL輪読会]BERT: Pre-training of Deep Bidirectional Transformers for Lang…
Read more GitHub - huggingface/pytorch-pretrained-BERT: The Big-&-Extending-Repository-of-Transformers: PyTorc...
Read more The Illustrated BERT, ELMo, and co. (How NLP Cracked Transfer Learning) – Jay Alammar – Visualizing ...