Abstract
Today, the knowledge base question answering (KB-QA) system is promising to achieve a large-scale high-quality reply in the e-commerce industry. However, there exist two major challenges to efficiently support large-scale KB-QA systems. On the one hand, it is difficult to serve tens of thousands of online stores (i.e., constrained by the tuning and deployment time), and it would perform poorly if the systems start without a sufficient number of chat records. On the other hand, current KB-QA systems cannot be updated in an efficient way due to the high cost of knowledge base (KB) updating. In this article, we propose an automatic learning scheme for KB-QA systems, called ALKB-QA, using a vector modeling method to address the preceding two main challenges. The ALKB-QA system provides online stores with basic KB templates that are suitable for many common occasions, and this feature enables the ability to deploy chatbots for a large number of online stores in a short time. Then, the KBs are further updated automatically to adapt to their own businesses (meet different specific needs), leading to increased reply accuracy. Our work has three main contributions. First, the proposed ALKB-QA system has a good business model in the e-commerce industry (serving tens of thousands of online stores with low cost), breaking the scalability limitations of existing KB-QA systems. Second, we assess the reply accuracy of the proposed ALKB-QA system using human evaluations, and the results show that it outperforms human annotation-base approaches. Third, we launched our ALKB-QA system as a real-world business application, and it supports tens of thousands of online stores.
- Jacob Andreas, Marcus Rohrbach, Trevor Darrell, and Dan Klein. 2016. Learning to compose neural networks for question answering. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 1545--1554. DOI:https://doi.org/10.18653/v1/N16-1181Google Scholar
Cross Ref
- Antoine Bordes, Sumit Chopra, and Jason Weston. 2014. Question answering with subgraph embeddings. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’14). 615--620.Google Scholar
Cross Ref
- Antoine Bordes, Jason Weston, and Nicolas Usunier. 2014. Open question answering with weakly supervised embedding models. In Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases. 165--180.Google Scholar
Cross Ref
- Heng Ji and Ralph Grishman. 2011. Knowledge base population: Successful approaches and challenges. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (Volume 1). 1148--1158.Google Scholar
- Yanyan Jia, Yansong Feng, Yuan Ye, Chao Lv, Chongde Shi, and Dongyan Zhao. 2018. Improved discourse parsing with two-step neural transition-based model. ACM Transactions on Asian and Low-Resour.ce Language Information Processing 17, 2 (Jan. 2018), Article 11, 21 pages. DOI:https://doi.org/10.1145/3152537Google Scholar
- Adam Lally, Sugato Bagchi, Michael Barborak, David W. Buchanan, Jennifer Chu-Carroll, David A. Ferrucci, Michael R. Glass, et al. 2017. WatsonPaths: Scenario-based question answering and inference over unstructured information. AI Magazine 38, 2 (2017), 59--76.Google Scholar
Cross Ref
- Xinyi Li, Yinchuan Li, Hongyang Yang, Liuqing Yang, and Xiao-Yang Liu. 2019. DP-LSTM: Differential privacy-inspired LSTM for stock prediction using financial news. In Proceedings of the NeurIPS Workshop on Robust AI in Financial Services: Data, Fairness, Explainability, Trustworthiness, and Privacy.Google Scholar
- Denis Lukovnikov, Asja Fischer, Jens Lehmann, and Sören Auer. 2017. Neural network-based question answering over knowledge graphs on word and character level. In Proceedings of the 26th International Conference on World Wide Web. 1211--1220.Google Scholar
Digital Library
- Yuning Mao, Xiang Ren, Jiaming Shen, Xiaotao Gu, and Jiawei Han. 2018. End-to-end reinforcement learning for automatic taxonomy induction. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2462--2472. DOI:https://doi.org/10.18653/v1/P18-1229Google Scholar
Cross Ref
- Bhaskar Mitra, Nick Craswell, et al. 2018. An introduction to neural information retrieval. Foundations and Trends® in Information Retrieval 13, 1 (2018), 1--126.Google Scholar
- Minghui Qiu, Feng-Lin Li, Siyu Wang, Xing Gao, Yan Chen, Weipeng Zhao, Haiqing Chen, Jun Huang, and Wei Chu. 2017. AliMe Chat: A sequence to sequence and rerank based chatbot engine. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 498--503.Google Scholar
Cross Ref
- Xipeng Qiu and Xuanjing Huang. 2015. Convolutional neural tensor network architecture for community-based question answering. In Proceedings of the 24th International Conference on Artificial Intelligence (IJCAI’15). 1305--1311.Google Scholar
Digital Library
- Stephen Robertson, Hugo Zaragoza, et al. 2009. The probabilistic relevance framework: BM25 and beyond. Foundations and Trends® in Information Retrieval 3, 4 (2009), 333--389.Google Scholar
- Lorenzo Rosasco, Ernesto De Vito, Andrea Caponnetto, Michele Piana, and Alessandro Verri. 2004. Are loss functions all the same? Neural Computation 16, 5 (2004), 1063--1076.Google Scholar
Digital Library
- Aliaksei Severyn and Alessandro Moschitti. 2015. Learning to rank short text pairs with convolutional deep neural networks. In Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, New York, NY, 373--382.Google Scholar
Digital Library
- Zhiguo Wang, Wael Hamza, and Radu Florian. 2017. Bilateral multi-perspective matching for natural language sentences. In Proceedings of the 26th International Joint Conference on Artificial Intelligence. 4144--4150.Google Scholar
Cross Ref
- Min-Chul Yang, Nan Duan, Ming Zhou, and Hae-Chang Rim. 2014. Joint relational embeddings for knowledge-based question answering. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’14). 645--650.Google Scholar
Cross Ref
- Shuo Yang, Lei Zou, Zhongyuan Wang, Jun Yan, and Ji-Rong Wen. 2017. Efficiently answering technical questions—A knowledge graph approach. In Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI’17). 3111--3118.Google Scholar
- Xuchen Yao and Benjamin Van Durme. 2014. Information extraction over structured data: Question answering with freebase. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 956--966.Google Scholar
Cross Ref
- Wen-Tau Yih, Ming-Wei Chang, Xiaodong He, and Jianfeng Gao. 2015. Semantic parsing via staged query graph generation: Question answering with knowledge base. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 1321--1331.Google Scholar
Cross Ref
- Adams Wei Yu, David Dohan, Minh-Thang Luong, Rui Zhao, Kai Chen, Mohammad Norouzi, and Quoc V. Le. 2018. QANet: Combining local convolution with global self-attention for reading comprehension. In Proceedings of the 6th International Conference on Learning Representations. 1211--1220.Google Scholar
Index Terms
Dynamic Updating of the Knowledge Base for a Large-Scale Question Answering System
Recommendations
Knowledge Base Question Answering System Based on Knowledge Graph Representation Learning
ICIAI '20: Proceedings of the 2020 the 4th International Conference on Innovation in Artificial IntelligenceKnowledge Base Question Answering (KBQA) refers that questions are answered by acquiring the relationship or entity from knowledge graph. The knowledge base is being high frequent used in modern question answering systems, which can find the exact ...
Core techniques of question answering systems over knowledge bases: a survey
The Semantic Web contains an enormous amount of information in the form of knowledge bases (KB). To make this information available, many question answering (QA) systems over KBs were created in the last years. Building a QA system over KBs is difficult ...
Structure-Aware Reasoning for Knowledge Base Question Answering
Advances in Knowledge Discovery and Data MiningAbstractAnswering question according to knowledge base (i.e. KBQA) has attracted extensive attention recently. Information retrieval is one of the mainstream methods for the KBQA task that first finds the topic entity in the question via entity linking ...






Comments