SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.04672 · 2021

Investigating Numeracy Learning Ability of a Text-to-Text Transfer Model

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
kuntalkumarpal/t5numeracy canonical 0 of 2
FunctionStatusWhere it lives
compute_exact_match Not yet run kuntalkumarpal/t5numeracy/code/decoding.py
code served (permissive licence) · get_code("9a405020adf1ed97")
value_to_label Not yet run kuntalkumarpal/t5numeracy/code/train_magnitude.py
code served (permissive licence) · get_code("f8542ff32f2e8f91")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2109.04672")
get_code_for_paper("2109.04672")
have("2109.04672")

Connect an agent — have() is free.