Archit Rathore, Yichu Zhou, Vivek Srikumar, Bei Wang
{"title":"TopoBERT:探索微调单词表示的拓扑结构","authors":"Archit Rathore, Yichu Zhou, Vivek Srikumar, Bei Wang","doi":"10.1177/14738716231168671","DOIUrl":null,"url":null,"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.","PeriodicalId":50360,"journal":{"name":"Information Visualization","volume":"22 1","pages":"186 - 208"},"PeriodicalIF":1.8000,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"TopoBERT: Exploring the topology of fine-tuned word representations\",\"authors\":\"Archit Rathore, Yichu Zhou, Vivek Srikumar, Bei Wang\",\"doi\":\"10.1177/14738716231168671\",\"DOIUrl\":null,\"url\":null,\"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.\",\"PeriodicalId\":50360,\"journal\":{\"name\":\"Information Visualization\",\"volume\":\"22 1\",\"pages\":\"186 - 208\"},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2023-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Information Visualization\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1177/14738716231168671\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, SOFTWARE ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Information Visualization","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1177/14738716231168671","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
TopoBERT: Exploring the topology of fine-tuned word representations
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.
期刊介绍:
Information Visualization is essential reading for researchers and practitioners of information visualization and is of interest to computer scientists and data analysts working on related specialisms. This journal is an international, peer-reviewed journal publishing articles on fundamental research and applications of information visualization. The journal acts as a dedicated forum for the theories, methodologies, techniques and evaluations of information visualization and its applications.
The journal is a core vehicle for developing a generic research agenda for the field by identifying and developing the unique and significant aspects of information visualization. Emphasis is placed on interdisciplinary material and on the close connection between theory and practice.
This journal is a member of the Committee on Publication Ethics (COPE).