Automated categorisation of patent claims that reference human genome sequences

Donglu Wang, Gabriela Ferraro, Hanna Suominen, Osmat A. Jefferson

Research output: A Conference proceeding or a Chapter in BookConference contribution

1 Citation (Scopus)

Abstract

Debates on gene patents have necessitated the analysis of patents that disclose and reference human sequences. In this study, we built an automated classifier that assigns sequences to one of nine predefined categories according to their functional roles in patent claims by applying natural language processing and supervised learning techniques. To improve its correctness, we experimented with various feature mappings, resulting in the maximal accuracy of 79%.

Original languageEnglish
Title of host publicationADCS 2014 - Proceedings of the 19th Australasian Document Computing Symposium
EditorsJ Shane Culpepper, Laurence Park, Guido Zuccon
Place of PublicationMelbourne
PublisherAssociation for Computing Machinery (ACM)
Pages117-120
Number of pages4
ISBN (Electronic)9781450330008
ISBN (Print)9781450330008
DOIs
Publication statusPublished - 26 Nov 2014
Event19th Australasian Document Computing Symposium, ADCS 2014 - Melbourne, Melbourne, Australia
Duration: 27 Nov 201428 Nov 2014

Publication series

NameACM International Conference Proceeding Series
Volume27-28-November-2014

Conference

Conference19th Australasian Document Computing Symposium, ADCS 2014
CountryAustralia
CityMelbourne
Period27/11/1428/11/14

Fingerprint Dive into the research topics of 'Automated categorisation of patent claims that reference human genome sequences'. Together they form a unique fingerprint.

Cite this