Transformers-based information extraction with limited data for domain-specific business documents. (January 2021)

• Record Type: Journal Article
• Authors: Nguyen, Minh-Tien; Le, Dung Tien; Le, Linh
• Is Part Of: Engineering applications of artificial intelligence. Volume 97(2021)
• Publication Date: 2021-01
• Subjects: Information extraction -- Transfer learning -- Transformers; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2020.104100
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Information extraction plays an important role for data transformation in business cases. However, building extraction systems in actual cases face two challenges: (i) the availability of labeled data is usually limited and (ii) highly detailed classification is required. This paper introduces a model for addressing the two challenges. Different from prior studies that usually require a large number of training samples, our extraction model is trained with a small number of data for extracting a large number of information types. To do that, the model takes into account the contextual aspect of pre-trained language models trained on a huge amount of data on general domains for word representation. To adapt to our downstream task, the model employs transfer learning by stacking Convolutional Neural Networks to learn hidden representation for classification. To confirm the efficiency of our method, we apply the model to two actual cases of document processing for bidding and sale documents of two Japanese companies. Experimental results on real testing sets show that, with a small number of training data, our model achieves high accuracy accepted by our clients.