LMFingerprints: Visual Explanations of Language Model Embedding Spaces through Layerwise Contextualization Scores

Loading...
Thumbnail Image
Date
2022
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
Language models, such as BERT, construct multiple, contextualized embeddings for each word occurrence in a corpus. Understanding how the contextualization propagates through the model's layers is crucial for deciding which layers to use for a specific analysis task. Currently, most embedding spaces are explained by probing classifiers; however, some findings remain inconclusive. In this paper, we present LMFingerprints, a novel scoring-based technique for the explanation of contextualized word embeddings. We introduce two categories of scoring functions, which measure (1) the degree of contextualization, i.e., the layerwise changes in the embedding vectors, and (2) the type of contextualization, i.e., the captured context information. We integrate these scores into an interactive explanation workspace. By combining visual and verbal elements, we provide an overview of contextualization in six popular transformer-based language models. We evaluate hypotheses from the domain of computational linguistics, and our results not only confirm findings from related work but also reveal new aspects about the information captured in the embedding spaces. For instance, we show that while numbers are poorly contextualized, stopwords have an unexpected high contextualization in the models' upper layers, where their neighborhoods shift from similar functionality tokens to tokens that contribute to the meaning of the surrounding sentences.
Description

CCS Concepts: Human-centered computing --> Visual analytics; Information visualization

        
@article{
10.1111:cgf.14541
, journal = {Computer Graphics Forum}, title = {{
LMFingerprints: Visual Explanations of Language Model Embedding Spaces through Layerwise Contextualization Scores
}}, author = {
Sevastjanova, Rita
and
Kalouli, Aikaterini-Lida
and
Beck, Christin
and
Hauptmann, Hanna
and
El-Assady, Mennatallah
}, year = {
2022
}, publisher = {
The Eurographics Association and John Wiley & Sons Ltd.
}, ISSN = {
1467-8659
}, DOI = {
10.1111/cgf.14541
} }
Citation
Collections