Multi-class Text Classification using BERT-based Active Learning
This addresses cost reduction in labeling for domain-specific applications like customer transaction classification, but it is incremental as it applies existing methods to a new context.
The paper tackled the problem of expensive manual labeling for multi-class text classification in pickup and delivery services by exploring BERT-based active learning strategies, achieving benchmarked performance on datasets including TREC-6 and AG's News Corpus.
Text Classification finds interesting applications in the pickup and delivery services industry where customers require one or more items to be picked up from a location and delivered to a certain destination. Classifying these customer transactions into multiple categories helps understand the market needs for different customer segments. Each transaction is accompanied by a text description provided by the customer to describe the products being picked up and delivered which can be used to classify the transaction. BERT-based models have proven to perform well in Natural Language Understanding. However, the product descriptions provided by the customers tend to be short, incoherent and code-mixed (Hindi-English) text which demands fine-tuning of such models with manually labelled data to achieve high accuracy. Collecting this labelled data can prove to be expensive. In this paper, we explore Active Learning strategies to label transaction descriptions cost effectively while using BERT to train a transaction classification model. On TREC-6, AG's News Corpus and an internal dataset, we benchmark the performance of BERT across different Active Learning strategies in Multi-Class Text Classification.