MEXN: Multi-Stage Extraction Network for Patent Document Classification
The patent document has different content for each paragraph, and the length of the document is also very long. Moreover, patent documents are classified hierarchically as multi-labels. Many works have employed deep neural architectures to classify the patent documents. Traditional document classifi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/18/6229 |
| _version_ | 1827706636843614208 |
|---|---|
| author | Juho Bai Inwook Shim Seog Park |
| author_facet | Juho Bai Inwook Shim Seog Park |
| author_sort | Juho Bai |
| collection | DOAJ |
| description | The patent document has different content for each paragraph, and the length of the document is also very long. Moreover, patent documents are classified hierarchically as multi-labels. Many works have employed deep neural architectures to classify the patent documents. Traditional document classification methods have not well represented the characteristics of entire patent document contents because they usually require a fixed input length. To address this issue, we propose a neural network-based document classification for patent documents by designing a novel multi-stage feature extraction network (MEXN), which comprise of paragraphs encoder and summarizer for all paragraphs. MEXN features analysis of the whole documents hierarchically and providing multi-labels outputs. Furthermore, MEXN preserves computing performance marginally increase. We demonstrate that the proposed method outperforms current state-of-the-art models in patent document classification tasks with multi-label classification experiments for USPD datasets. |
| first_indexed | 2024-03-10T16:29:19Z |
| format | Article |
| id | doaj.art-115bf7b5a5d344e19ec2f5975da9e0d9 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T16:29:19Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-115bf7b5a5d344e19ec2f5975da9e0d92023-11-20T12:57:13ZengMDPI AGApplied Sciences2076-34172020-09-011018622910.3390/app10186229MEXN: Multi-Stage Extraction Network for Patent Document ClassificationJuho Bai0Inwook Shim1Seog Park2Department of Computer Science and Engineering, Sogang University, Mapo-gu, Seoul 04107, KoreaThe Ground Autonomy Laboratory, Agency for Defense Development, Daejeon 34186, KoreaDepartment of Computer Science and Engineering, Sogang University, Mapo-gu, Seoul 04107, KoreaThe patent document has different content for each paragraph, and the length of the document is also very long. Moreover, patent documents are classified hierarchically as multi-labels. Many works have employed deep neural architectures to classify the patent documents. Traditional document classification methods have not well represented the characteristics of entire patent document contents because they usually require a fixed input length. To address this issue, we propose a neural network-based document classification for patent documents by designing a novel multi-stage feature extraction network (MEXN), which comprise of paragraphs encoder and summarizer for all paragraphs. MEXN features analysis of the whole documents hierarchically and providing multi-labels outputs. Furthermore, MEXN preserves computing performance marginally increase. We demonstrate that the proposed method outperforms current state-of-the-art models in patent document classification tasks with multi-label classification experiments for USPD datasets.https://www.mdpi.com/2076-3417/10/18/6229document classificationautomatic patent classification systemattention network |
| spellingShingle | Juho Bai Inwook Shim Seog Park MEXN: Multi-Stage Extraction Network for Patent Document Classification Applied Sciences document classification automatic patent classification system attention network |
| title | MEXN: Multi-Stage Extraction Network for Patent Document Classification |
| title_full | MEXN: Multi-Stage Extraction Network for Patent Document Classification |
| title_fullStr | MEXN: Multi-Stage Extraction Network for Patent Document Classification |
| title_full_unstemmed | MEXN: Multi-Stage Extraction Network for Patent Document Classification |
| title_short | MEXN: Multi-Stage Extraction Network for Patent Document Classification |
| title_sort | mexn multi stage extraction network for patent document classification |
| topic | document classification automatic patent classification system attention network |
| url | https://www.mdpi.com/2076-3417/10/18/6229 |
| work_keys_str_mv | AT juhobai mexnmultistageextractionnetworkforpatentdocumentclassification AT inwookshim mexnmultistageextractionnetworkforpatentdocumentclassification AT seogpark mexnmultistageextractionnetworkforpatentdocumentclassification |