2005
DOI: 10.1016/j.wpi.2004.08.001
|View full text |Cite
|
Sign up to set email alerts
|

The impact of metadata on the accuracy of automated patent classification

Abstract: This is the accepted version of the paper.This version of the publication may differ from the final published version. Permanent repository link AbstractDuring the last decade, the advance of machine learning tools and algorithms has resulted in tremendous progress in the automated classification of documents. However, many classifiers base their classification decisions solely on document text and ignore metadata (such as authors, publication date, and author affiliation). In this project, automated classifi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
3
0

Year Published

2010
2010
2023
2023

Publication Types

Select...
3
3
3

Relationship

0
9

Authors

Journals

citations
Cited by 21 publications
(5 citation statements)
references
References 16 publications
0
3
0
Order By: Relevance
“…For CPC classification, various datasets are available (Pujari et al, 2021(Pujari et al, , 2022Li et al, 2018). Similar to our target classification task, Richter and MacFarlane (2005) study classification for a patent alert system for the biochemical domain, but the dataset was not open-sourced. Sharma et al (2019) provide a patent dataset with human-written abstractive summaries.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…For CPC classification, various datasets are available (Pujari et al, 2021(Pujari et al, , 2022Li et al, 2018). Similar to our target classification task, Richter and MacFarlane (2005) study classification for a patent alert system for the biochemical domain, but the dataset was not open-sourced. Sharma et al (2019) provide a patent dataset with human-written abstractive summaries.…”
Section: Related Workmentioning
confidence: 99%
“…Embedding Metadata for Patent Classification. In the contexts of classification (Richter and MacFarlane, 2005;Benites et al, 2018) and clustering (Vlase et al, 2012), non-neural count-and TF-IDF-based feature vectors reflecting IPC, inventor, and assignee information have been proposed. For CPC classification, Niu and Cai (2019) leverage the BM25-similarity between the document text and the CPC label descriptions.…”
Section: Related Workmentioning
confidence: 99%
“…A large number of scholars at home and abroad have studied the algorithm of patent text classification. RICHTER G [5] used KNN method to automatically classify patent text, improving the classification accuracy from 70.8% to 75.4%; Hu Jie [6] and others proposed a patent text classification model based on convolutional neural network and random forest, which is superior to other single models in English machinery patent classification. Li Sheng zhen [7] proposed an automatic patent classification method based on the back propagation neural network.…”
Section: Introductionmentioning
confidence: 99%
“…Patent classifications are a tool for the patent process. The human process related to assigning classes to patents is valuable in the patenting process, even to the extent that automated classifications fall short of providing similar results [16]. However, focusing on strategic foresight and patent management, patent classification represents an inadequate measure that could satisfy the needs of corporate planning [1,12].…”
Section: Introductionmentioning
confidence: 99%