Similarity Analysis of Contextual Word Representation Models

By John Wu, Yonatan Belinkov, Hassan Sajjad, Nadir Durrani, Fahim Dalvi, James R. Glass. 2020

85 citations recorded by the source corpus.

This paper investigates contextual word representation models from the lens of similarity analysis. Given a collection of trained models, we measure the similarity of their internal representations and attention. Critically, these models come from vastly different architectures. We use existing and novel similarity measures that aim to gauge the level of localization of information in the deep models, and facilitate the investigation of which design factors affect model similarity, without requiring any external linguistic annotation. The analysis reveals that models within the same family are more similar to one another, as may be expected. Surprisingly, different architectures have rather similar representations, but different individual neurons. We also observed differences in information localization in lower and higher layers and found that higher layers are more affected by fine-tuning on downstream tasks.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

Citations in the corpus

Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth (2020, background): “…dynamics (Maheswaranathan et al., 2019) to revealing hidden linguistic structure in large language models (Bau et al., 2019; Kudugunta et al., 2019; Wu et al., 2019; 2020) to applications in neuroscience (Shi et al., 2019; Li et al., 2019; Merel et al., 2019; Zhang & Bellec, 2020) and medicine…”
Analyzing Individual Neurons in Pre-trained Language Models (2020, unknown): “Recently, Wu et al. (2020) measured similarity of internal representations and attention across prominent contex-tualized representations (from BERT, ELMo, etc.).”
Do Vision Transformers See Like Convolutional Neural Networks? (2021, unknown): “These techniques have been very successful in providing insights on properties of different vision architectures [29, 22, 18], representation structure in language models [48, 25, 47, 21], dynamics of training methods [33, 24] and domain specific model behavior [27, 35, 38].”
Analyzing Redundancy in Pretrained Transformer Models (2020, methodology): “This has also been alluded to by others (Hao et al., 2019; Wu et al., 2020).”