Enhancement of Question Answering System Accuracy via Transfer Learning and BERT
Open Access
- 13 November 2022
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 12 (22) , 11522
Abstract
Entity linking and predicate matching are two core tasks in the Chinese Knowledge Base Question Answering (CKBQA). Compared with the English entity linking task, the Chinese entity linking is extremely complicated, making accurate Chinese entity linking difficult. Meanwhile, strengthening the correlation between entities and predicates is the key to the accuracy of the question answering system. Therefore, we put forward a Bidirectional Encoder Representation from Transformers and transfer learning Knowledge Base Question Answering (BAT-KBQA) framework, which is on the basis of feature-enhanced Bidirectional Encoder Representation from Transformers (BERT), and then perform a Named Entity Recognition (NER) task, which is appropriate for Chinese datasets using transfer learning and the Bidirectional Long Short-Term Memory-Conditional Random Field (BiLSTM-CRF) model. We utilize a BERT-CNN (Convolutional Neural Network) model for entity disambiguation of the problem and candidate entities; based on the set of entities and predicates, a BERT-Softmax model with answer entity predicate features is introduced for predicate matching. The answer ultimately chooses to integrate entities and predicates scores to determine the definitive answer. The experimental results indicate that the model, which is developed by us, considerably enhances the overall performance of the Knowledge Base Question Answering (KBQA) and it has the potential to be generalizable. The model also has better performance on the dataset supplied by the NLPCC-ICCPOL2016 KBQA task with a mean F1 score of 87.74% compared to BB-KBQA.Keywords
Funding Information
- National Key R&D Program of China (2021YFB3500100, 52250005, 21875271, U20B2021, 21707147, 51372046, 51479037, 91226202, 91426304, 2022C01236, 2019C01060, 2015ZX06004-001, 2014A610006, 2016A610273, 2019A610106)
- National Natural Science Foundations of China (2021YFB3500100, 52250005, 21875271, U20B2021, 21707147, 51372046, 51479037, 91226202, 91426304, 2022C01236, 2019C01060, 2015ZX06004-001, 2014A610006, 2016A610273, 2019A610106)
- Key R&D Projects of Zhejiang Province (2021YFB3500100, 52250005, 21875271, U20B2021, 21707147, 51372046, 51479037, 91226202, 91426304, 2022C01236, 2019C01060, 2015ZX06004-001, 2014A610006, 2016A610273, 2019A610106)
- Entrepreneurship Program of Foshan National Hi-tech Industrial Development Zone, the Major Project of the Ministry of Science and Technology of China (2021YFB3500100, 52250005, 21875271, U20B2021, 21707147, 51372046, 51479037, 91226202, 91426304, 2022C01236, 2019C01060, 2015ZX06004-001, 2014A610006, 2016A610273, 2019A610106)
- Ningbo Natural Science Foundations (2021YFB3500100, 52250005, 21875271, U20B2021, 21707147, 51372046, 51479037, 91226202, 91426304, 2022C01236, 2019C01060, 2015ZX06004-001, 2014A610006, 2016A610273, 2019A610106)
This publication has 34 references indexed in Scilit:
- A Deep Learning Approach for Question Answering Over Knowledge Base2016
- Neural Architectures for Named Entity Recognition2016
- WikidataCommunications of the ACM, 2014
- An Introduction to Question Answering over Linked Data2014
- ArnetMiner2008
- Freebase2008
- Yago2007
- Long Short-Term MemoryNeural Computation, 1997
- Artificial ParanoiaArtificial Intelligence, 1971
- ELIZA—a computer program for the study of natural language communication between man and machineCommunications of the ACM, 1966