Semantic Patent Classification Using Stack Generalization of Deep Models

Over the past few years, there has been a significant increase in patent applications, which has resulted in a heavier workload for examination offices in examining and prosecuting these inventions. To adequately perform this legal process, examiners must thoroughly analyze patents by manually ident...

Full description

Saved in:
Bibliographic Details
Main Author: Shahla Nemati
Format: Article
Language:English
Published: University of science and culture 2024-04-01
Series:International Journal of Web Research
Subjects:
Online Access:https://ijwr.usc.ac.ir/article_205645_b0073e19f1fd6c98896e60593a4fbf5d.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850099327063556096
author Shahla Nemati
author_facet Shahla Nemati
author_sort Shahla Nemati
collection DOAJ
description Over the past few years, there has been a significant increase in patent applications, which has resulted in a heavier workload for examination offices in examining and prosecuting these inventions. To adequately perform this legal process, examiners must thoroughly analyze patents by manually identifying the semantic information such as problem description and solutions. The process of manually annotating is both tedious and time-consuming. To solve this issue, we have introduced a deep ensemble model for semantic paragraph-level pattern classification based on the semantic content of patents. Specifically, our proposed model classifies the paragraphs into semantic categories to facilitate the annotation process. The proposed model employs stack generalization as an ensemble method for combining various deep models such as Long Short-Term Memories (LSTM), bidirectional LSTM (BiLSTM), Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and the pre-trained BERT model. We compared the proposed model with several baselines and state-of-the-art deep models on the PaSA dataset containing 150000 USPTO patents classified into three classes of 'technical advantages', 'technical problems', and 'other boilerplate text'. The results of extensive experiments show that the proposed model outperforms both traditional and state-of-the-art deep models significantly.
format Article
id doaj-art-e5a5aa7b8acf4ef3830a882417840f0a
institution DOAJ
issn 2645-4343
language English
publishDate 2024-04-01
publisher University of science and culture
record_format Article
series International Journal of Web Research
spelling doaj-art-e5a5aa7b8acf4ef3830a882417840f0a2025-08-20T02:40:30ZengUniversity of science and cultureInternational Journal of Web Research2645-43432024-04-017211210.22133/ijwr.2024.449332.1210Semantic Patent Classification Using Stack Generalization of Deep ModelsShahla Nemati0https://orcid.org/0000-0003-2906-5871Department of Computer Engineering, Faculty of Engineering Shahrekord University Shahrekord, IranOver the past few years, there has been a significant increase in patent applications, which has resulted in a heavier workload for examination offices in examining and prosecuting these inventions. To adequately perform this legal process, examiners must thoroughly analyze patents by manually identifying the semantic information such as problem description and solutions. The process of manually annotating is both tedious and time-consuming. To solve this issue, we have introduced a deep ensemble model for semantic paragraph-level pattern classification based on the semantic content of patents. Specifically, our proposed model classifies the paragraphs into semantic categories to facilitate the annotation process. The proposed model employs stack generalization as an ensemble method for combining various deep models such as Long Short-Term Memories (LSTM), bidirectional LSTM (BiLSTM), Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and the pre-trained BERT model. We compared the proposed model with several baselines and state-of-the-art deep models on the PaSA dataset containing 150000 USPTO patents classified into three classes of 'technical advantages', 'technical problems', and 'other boilerplate text'. The results of extensive experiments show that the proposed model outperforms both traditional and state-of-the-art deep models significantly.https://ijwr.usc.ac.ir/article_205645_b0073e19f1fd6c98896e60593a4fbf5d.pdfpatent semantic analysisdeep learningpatent information retrievalnatural language processing (nlp)
spellingShingle Shahla Nemati
Semantic Patent Classification Using Stack Generalization of Deep Models
International Journal of Web Research
patent semantic analysis
deep learning
patent information retrieval
natural language processing (nlp)
title Semantic Patent Classification Using Stack Generalization of Deep Models
title_full Semantic Patent Classification Using Stack Generalization of Deep Models
title_fullStr Semantic Patent Classification Using Stack Generalization of Deep Models
title_full_unstemmed Semantic Patent Classification Using Stack Generalization of Deep Models
title_short Semantic Patent Classification Using Stack Generalization of Deep Models
title_sort semantic patent classification using stack generalization of deep models
topic patent semantic analysis
deep learning
patent information retrieval
natural language processing (nlp)
url https://ijwr.usc.ac.ir/article_205645_b0073e19f1fd6c98896e60593a4fbf5d.pdf
work_keys_str_mv AT shahlanemati semanticpatentclassificationusingstackgeneralizationofdeepmodels