Grinding Gears

Text classification is often done through fine-tuning of a pretrained foundation model with domain-specific data. In FreeAgent we use transformer based models to automatically classify incoming bank transactions. Specifically we use a DistilBERT model that is fine-tuned on hundreds of millions of bank transactions with customer-labelled accounting categories. The model inputs are currently text-based, built from a combination of bank transaction descriptions and amounts. In this post we describe an approach to fine-tuning the DistilBERT model and training the classifier including the numerical amount feature as a single network. Continue reading

Classification with transformer models A common approach for classification tasks with text data is to fine-tune a pre-trained transformer model on domain-specific data. At FreeAgent we apply this approach to automatically categorise bank transactions, using raw inputs that are a mixture of text, numerical and categorical data types.    The current approach is to concatenate the input features for each transaction into a single string before passing to the model.  For… Continue reading

In this post I'll describe how we train our Hugging Face models in a fraction of the time with a data parallel approach. Continue reading

This post describes our approach to fine-tuning a BERT model for multiclass categorisation with Hugging Face and Amazon SageMaker. Continue reading