The Effectiveness of Bidirectional Generative Patent Language Models

Jieh Sheng Lee*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Generative patent language models can assist humans to write patent text more effectively. The question is how to measure effectiveness from a human-centric perspective and how to improve effectiveness. In this manuscript, a simplified design of the autocomplete function is proposed to increase effectiveness by more than 10%. With the simplified design, the effectiveness of autocomplete can reach more than 60%, which means that more than 60% of keystrokes can be saved by autocomplete. Since writing patent text does not necessarily start from the beginning to the end, a question is whether the generative model can assist a user no matter where to start writing. To answer the question, the generative models in this manuscript are pre-trained with training data in both directions. The generative models become bidirectional. Since text generation is bidirectional, the calculation of autocomplete effectiveness can be bidirectional and starts from anywhere in the text. After thorough experiments, a key finding is that the autocomplete effectiveness of a model for the same text remains similar no matter where the calculation starts. The finding indicates that such bidirectional models can assist a user at a similar level, no matter where the user starts to write.

Original languageEnglish
Title of host publicationLegal Knowledge and Information Systems - JURIX 2022
Subtitle of host publicationThe 35th Annual Conference
EditorsEnrico Francesconi, Georg Borges, Christoph Sorge
PublisherIOS Press BV
Pages194-199
Number of pages6
ISBN (Electronic)9781643683645
DOIs
StatePublished - 5 Dec 2022
Event35th International Conference on Legal Knowledge and Information Systems, JURIX 2022 - Saarbrucken, Germany
Duration: 14 Dec 202216 Dec 2022

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume362
ISSN (Print)0922-6389
ISSN (Electronic)1879-8314

Conference

Conference35th International Conference on Legal Knowledge and Information Systems, JURIX 2022
Country/TerritoryGermany
CitySaarbrucken
Period14/12/2216/12/22

Keywords

  • Artificial Intelligence
  • Deep Learning
  • Natural Language Generation
  • Natural Language Processing
  • Patent

Fingerprint

Dive into the research topics of 'The Effectiveness of Bidirectional Generative Patent Language Models'. Together they form a unique fingerprint.

Cite this