Controlling Patent Text Generation by Structural Metadata

Jieh-Sheng Lee*

*此作品的通信作者

研究成果: Conference contribution同行評審

6 引文 斯高帕斯(Scopus)

摘要

The ultimate goal of my long-term project is "Augmented Inventing." This work is a follow-up effort toward the goal. It leverages the structural metadata in patent documents and the text-to-text mappings between metadata. The structural metadata includes patent title, abstract, independent claim, and dependent claim. By using the structural metadata, it is possible to control what kind of patent text to generate. By using the text-to-text mapping, it is possible to let a generative model generate one type of patent text from another type of patent text. Furthermore, through multiple mappings, it is possible to build a text generation flow, for example, generating from a few words to a patent title, from the title to an abstract, from the abstract to an independent claim, and from the independent claim to multiple dependent claims. The text generation flow can also go backward after training with bi-directional mappings. In addition to those above, the contributions of this work include: (1) released four generative models trained with patent corpus from scratch, (2) released the sample code to demonstrate how to generate patent text bi-directionally, (3) measuring the performances of the models by ROGUE and Universal Sentence Encoder as preliminary evaluations of text generation quality.

原文English
主出版物標題CIKM 2020 - Proceedings of the 29th ACM International Conference on Information and Knowledge Management
發行者Association for Computing Machinery
頁面3241-3244
頁數4
ISBN(電子)9781450368599
DOIs
出版狀態Published - 19 10月 2020
事件29th ACM International Conference on Information and Knowledge Management, CIKM 2020 - Virtual, Online, Ireland
持續時間: 19 10月 202023 10月 2020

出版系列

名字International Conference on Information and Knowledge Management, Proceedings

Conference

Conference29th ACM International Conference on Information and Knowledge Management, CIKM 2020
國家/地區Ireland
城市Virtual, Online
期間19/10/2023/10/20

指紋

深入研究「Controlling Patent Text Generation by Structural Metadata」主題。共同形成了獨特的指紋。

引用此