A Hierarchical Neural Network for Information Extraction of Product Attribute and Condition Sentences
Yukinori Homma, Kugatsu Sadamitsu, Kyosuke Nishida, Ryuichiro Higashinaka, Hisako Asano, Yoshihiro Matsuo
Abstract
This paper describes a hierarchical neural network we propose for sentence classification to extract product information from product documents. The network classifies each sentence in a document into attribute and condition classes on the basis of word sequences and sentence sequences in the document. Experimental results showed the method using the proposed network significantly outperformed baseline methods by taking semantic representation of word and sentence sequential data into account. We also evaluated the network with two different product domains (insurance and tourism domains) and found that it was effective for both the domains.- Anthology ID:
- W16-4403
- Volume:
- Proceedings of the Open Knowledge Base and Question Answering Workshop (OKBQA 2016)
- Month:
- December
- Year:
- 2016
- Address:
- Osaka, Japan
- Editors:
- Key-Sun Choi, Christina Unger, Piek Vossen, Jin-Dong Kim, Noriko Kando, Axel-Cyrille Ngonga Ngomo
- Venue:
- WS
- SIG:
- Publisher:
- The COLING 2016 Organizing Committee
- Note:
- Pages:
- 21–29
- Language:
- URL:
- https://preview.aclanthology.org/add_missing_videos/W16-4403/
- DOI:
- Cite (ACL):
- Yukinori Homma, Kugatsu Sadamitsu, Kyosuke Nishida, Ryuichiro Higashinaka, Hisako Asano, and Yoshihiro Matsuo. 2016. A Hierarchical Neural Network for Information Extraction of Product Attribute and Condition Sentences. In Proceedings of the Open Knowledge Base and Question Answering Workshop (OKBQA 2016), pages 21–29, Osaka, Japan. The COLING 2016 Organizing Committee.
- Cite (Informal):
- A Hierarchical Neural Network for Information Extraction of Product Attribute and Condition Sentences (Homma et al., 2016)
- PDF:
- https://preview.aclanthology.org/add_missing_videos/W16-4403.pdf