Investigating Numeracy Learning Ability of a Text-to-Text Transfer Model
This work addresses the challenge of numerical understanding in NLP models, which is crucial for applications requiring accurate numeracy, but it is incremental as it builds on existing T5 models.
The study investigated the numeracy learning ability of the T5 text-to-text transfer model, finding that while it performs reasonably well in interpolation settings, it struggles significantly in extrapolation across four numeracy tasks.
The transformer-based pre-trained language models have been tremendously successful in most of the conventional NLP tasks. But they often struggle in those tasks where numerical understanding is required. Some possible reasons can be the tokenizers and pre-training objectives which are not specifically designed to learn and preserve numeracy. Here we investigate the ability of text-to-text transfer learning model (T5), which has outperformed its predecessors in the conventional NLP tasks, to learn numeracy. We consider four numeracy tasks: numeration, magnitude order prediction, finding minimum and maximum in a series, and sorting. We find that, although T5 models perform reasonably well in the interpolation setting, they struggle considerably in the extrapolation setting across all four tasks.