Technological taxonomies for hypernym and hyponym retrieval in patent texts

TL;DR

This paper introduces an automatic method for creating extensive technological taxonomies from patent texts using CPC classifications and fine-tuned T5 models, enabling dynamic updates and high-precision hypernym/hyponym retrieval.

Contribution

It presents a large, freely available taxonomy of 170k nodes across nine technological branches and demonstrates the effectiveness of fine-tuned T5 models for hypernym and hyponym extraction.

Findings

Taxonomy contains about 170,000 nodes across 9 branches.

T5 model achieves high precision in hypernym/hyponym generation.

Resource is updateable with new technological terms.

Abstract

This paper presents an automatic approach to creating taxonomies of technical terms based on the Cooperative Patent Classification (CPC). The resulting taxonomy contains about 170k nodes in 9 separate technological branches and is freely available. We also show that a Text-to-Text Transfer Transformer (T5) model can be fine-tuned to generate hypernyms and hyponyms with relatively high precision, confirming the manually assessed quality of the resource. The T5 model opens the taxonomy to any new technological terms for which a hypernym can be generated, thus making the resource updateable with new terms, an essential feature for the constantly evolving field of technological terminology.