TopoBERT: Exploring the topology of fine-tuned word representations. (July 2023)

• Record Type: Journal Article
• Authors: Rathore, Archit; Zhou, Yichu; Srikumar, Vivek; Wang, Bei
• Is Part Of: Information visualization. Volume 22:Number 3(2023)
• Page Start: 186
• Page End: 208
• Publication Date: 2023-07
• Subjects: Visualization -- topological data analysis -- transformers -- language models -- BERT -- word representations; Information visualization -- Periodicals; 006.605
• DOI: 10.1177/14738716231168671
• Languages: English
• ISSNs: 1473-8716

Abstract

Transformer-based language models such as BERT and its variants have found widespread use in natural language processing (NLP). A common way of using these models is to fine-tune them to improve their performance on a specific task. However, it is currently unclear how the fine-tuning process affects the underlying structure of the word embeddings from these models. We present TopoBERT, a visual analytics system for interactively exploring the fine-tuning process of various transformer-based models – across multiple fine-tuning batch updates, subsequent layers of the model, and different NLP tasks – from a topological perspective. The system uses the mapper algorithm from topological data analysis (TDA) to generate a graph that approximates the shape of a model's embedding space for an input dataset. TopoBERT enables its users (e.g. experts in NLP and linguistics) to (1) interactively explore the fine-tuning process across different model-task pairs, (2) visualize the shape of embedding spaces at multiple scales and layers, and (3) connect linguistic and contextual information about the input dataset with the topology of the embedding space. Using TopoBERT, we provide various use cases to exemplify its applications in exploring fine-tuned word embeddings. We further demonstrate the utility of TopoBERT, which enables users to generate insights about the fine-tuning process and provides support for empirical validation of these insights.