Sofean, Mustafa

2020-06-27T18:04:52Z

2019

<div class="csl-bib-body"> <div class="csl-entry">Sofean, M. (2019). Deep Learning based Pipeline with Multichannel Inputs for Patent Classification. In <i>Proceedings of The 1st Workshop on Patent Text Mining and Semantic Technologies (PatentSemTech 2019)</i>. 1st Workshop on Patent Text Mining and Semantic Technologies (PatentSemTech 2019), Karlsruhe, Germany. https://doi.org/10.34726/pst2019.5</div> </div>

https://doi.org/10.34726/pst2019.5

http://hdl.handle.net/20.500.12708/830

Patent document classification as groundwork has been a challenging task with no satisfactory performance for decades. In this work, we introduce a deep learning pipeline for automatic patent classification with multichannel inputs based on LSTM and word vector embeddings. Sophisticated text mining methods are used to extract the most important segments from patent texts, and a domain-specific pre-trained word embeddings model for the patent domain is developed; it was trained on a very large dataset of more than five million patents. A deep neural network model is trained with multichannel inputs namely embeddings of different segments of patent texts, and sparse linear input of different metadata. A series of patent classification experiments are conducted on different patent datasets, and the experimental results indicate that using the segments of patent texts as well as the metadata as multichannel inputs for a deep neuralnetwork model, achieves better performance than one input channel.

English

en

http://creativecommons.org/licenses/by/4.0/

Patent Analysis

Neural Network

Deep Learning

Patent Classification

Deep Learning based Pipeline with Multichannel Inputs for Patent Classification

Inproceedings

Konferenzbeitrag

Creative Commons Namensnennung 4.0 International

Creative Commons Attribution 4.0 International

10.34726/pst2019.5

Authors 2019

Full-Paper Contribution

Karlsruhe, Germany

Proceedings of The 1st Workshop on Patent Text Mining and Semantic Technologies (PatentSemTech 2019)

vor

AC15614273

2

urn:nbn:at:at-ubtuw:3-9441

CC BY 4.0

CC BY 4.0

1st Workshop on Patent Text Mining and Semantic Technologies (PatentSemTech 2019)

12-09-2019

12-09-2019

On Site

Event for scientific audience

Karlsruhe

DE

Sofean, Mustafa

en

conference paper

open

with Fulltext

Publications

http://purl.org/coar/resource_type/c_5794

Open Access