Domain Knowledge Graph Question Answering Based on Semantic Analysis and Data Augmentation
Source abstract
Abstract
Information retrieval-based question answering (IRQA) and knowledge-based question answering (KBQA) are the main forms of question answering (QA) systems. The answer generated by the IRQA system is extracted from the relevant text but has a certain degree of randomness, while the KBQA system retrieves the answer from structured data, and its accuracy is relatively high. In the field of policy and regulations such as household registration, the QA system requires precise and rigorous answers. Therefore, we design a QA system based on the household registration knowledge graph, aiming to provide rigorous and accurate answers for relevant household registration inquiries. The QA system uses a semantic analysis-based approach to simplify one question into a simple problem consisting of a single event entity and a single intention relationship, and quickly generates accurate answers by searching in the household registration knowledge graph. Due to the scarcity and imbalance of QA corpus data in the field of household registration, we use GPT3.5 to augment the collected questions dataset and explore the impact of data augmentation on the QA system. The experiment results show that the accuracy rate of the QA system using the augmented dataset reaches 93%, which is 6% higher than before.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Topic Modeling · Advanced Graph Neural Networks · Data Quality and Management
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Automation, Wuhan University of Technology, Wuhan 430062, China
Funding
Science and Technology Department of Hubei Province
References (59)
Show source-provided references
1. Answer Category-Aware Answer Selection for Question Answering10.1109/ACCESS.2020.3034920 ↗
2. Jurafsky, D., and Martin, J.H. (2014). Speech and Language Processing, Pearson.
3. OpenAI (2023). GPT-4 Technical Report. arXiv.
4. Zeng, A., Liu, X., Du, Z., Wang, Z., Lai, H., Ding, M., Yang, Z., Xu, Y., Zheng, W., and Xia, X. (2022). Glm-130b: An open bilingual pre-trained model. arXiv.
5. Geographies of self and other: Mapping Japan through the koseki
6. The Making of the Civil Registration Act of 183610.1017/S002204690004505X ↗
7. Che, W., Feng, Y., Qin, L., and Liu, T. (2021, January 7–11). N-LTP: An Open-source Neural Language Technology Platform for Chinese. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (Emnlp 2021): Proceedings of System Demonstrations, Punta Cana, Dominican Republic.10.18653/v1/2021.emnlp-demo.6 ↗
8. Bordes, A., Usunier, N., Chopra, S., and Weston, J. (2015). Large-scale simple question answering with memory networks. arXiv.
9. Bao, J., Duan, N., Yan, Z., Zhou, M., and Zhao, T. (2016, January 11–16). Constraint-based question answering with knowledge graph. Proceedings of the COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, Osaka, Japan.
10. Unger, C., Bühmann, L., Lehmann, J., Ngomo, A.-C.N., Gerber, D., and Cimiano, P. (2012, January 16–20). Template-Based Question Answering over RDF Data. Proceedings of the 21st International Conference on World Wide Web, WWW’12, Lyon, France.10.1145/2187836.2187923 ↗
11. Zheng, W., Zou, L., Lian, X., Yu, J.X., Song, S., and Zhao, D. (June, January 31). How to Build Templates for RDF Question/Answering: An Uncertain Graph Similarity Join Approach. Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, SIGMOD’15, Melbourne, Australia.10.1145/2723372.2747648 ↗
12. Cui, W., Xiao, Y., Wang, H., Song, Y., Hwang, S., and Wang, W. (2019). KBQA: Learning question answering over QA corpora and knowledge bases. arXiv.
13. Bast, H., and Haussmann, E. (2015, January 18–23). More accurate question answering on freebase. Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, Melbourne, Australia.10.1145/2806416.2806472 ↗
14. Abujabal, A., Yahya, M., Riedewald, M., and Weikum, G. (2017, January 3–7). Automated template generation for question answering over knowledge graphs. Proceedings of the 26th International Conference on World Wide Web, Perth, Australia.10.1145/3038912.3052583 ↗
15. Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., and Zhang, C. (1995, January 20–23). Learning efficient convolutional networks through network slimming. Proceedings of the IEEE International Conference on Computer Vision, Cambridge, MA, USA.
16. Outlining and Filling: Hierarchical Query Graph Generation for Answering Complex Questions Over Knowledge Graphs10.1109/TKDE.2022.3207477 ↗
17. Xu, K., Wu, L., Wang, Z., Yu, M., Chen, L., and Sheinin, V. (2018). Exploiting rich syntactic information for semantic parsing with graph-to-sequence model. arXiv.10.18653/v1/D18-1110 ↗
18. Green, B., Wolf, A., Chomsky, C., and Laughery, K. (1986). Readings in Natural Language Processing, Morgan Kaufmann Publishers Inc.
19. Lunar rocks in natural english: Explorations in natural language question answering
20. Wikidata: A free collaborative knowledgebase10.1145/2629489 ↗
21. DBpedia–A large-scale, multilingual knowledge base extracted from Wikipedia10.3233/SW-140134 ↗
22. Bollacker, K., Evans, C., Paritosh, P., Sturge, T., and Taylor, J. (2008, January 9–12). Freebase: A collaboratively created graph database for structuring human knowledge. Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, Vancouver, BC, Canada.10.1145/1376616.1376746 ↗
23. Lukovnikov, D., Fischer, A., Lehmann, J., and Auer, S. (2017, January 3–7). Neural network-based question answering over knowledge graphs on word and character level. Proceedings of the 26th International Conference on World Wide Web, Perth, Australia.10.1145/3038912.3052675 ↗
24. Deng, Y., Zhang, W., Xu, W., Shen, Y., and Lam, W. (IEEE Trans. Neural Networks Learn. Syst., 2023). Nonfactoid Question Answering as Query-Focused Summarization with Graph-Enhanced Multihop Inference, IEEE Trans. Neural Networks Learn. Syst., early access.10.1109/TNNLS.2023.3258413 ↗
25. Modeling relation paths for knowledge graph completion10.1109/TKDE.2020.2970044 ↗
26. Knowledge graph embedding: A survey of approaches and applications10.1109/TKDE.2017.2754499 ↗
27. Domain-specific knowledge graphs: A survey10.1016/j.jnca.2021.103076 ↗
28. A survey on knowledge graphs: Representation, acquisition, and applications10.1109/TNNLS.2021.3070843 ↗
29. Research on Medical Question Answering System Based on Knowledge Graph10.1109/ACCESS.2021.3055371 ↗
30. Question answering system of electric business field based on Chinese knowledge map
31. Question answering over knowledge graphs: A case study in tourism10.1109/ACCESS.2022.3187178 ↗
32. Knowledge graph construction techniques
33. (2023, June 09). Wuhan City Household Registration Business Processing Guidelines, Available online: http://www.wuhan.gov.cn/gfxwj/sbmgfxwj/sgaj_79493/202301/t20230104_2124417.shtml.
34. Speer, R., Chin, J., and Havasi, C. (2017, January 4–9). Conceptnet 5.5: An open multilingual graph of general knowledge. Proceedings of the AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.10.1609/aaai.v31i1.11164 ↗
35. (2023, June 09). Hubei Government Service Network, Available online: http://zwfw.hubei.gov.cn/.
36. GMNet: Graded-feature multilabel-learning network for RGB-thermal urban scene semantic segmentation10.1109/TIP.2021.3109518 ↗
37. Dual-level representation enhancement on characteristic and context for image-text retrieval10.1109/TCSVT.2022.3182426 ↗
38. Dual-interactive fusion for code-mixed deep representation learning in tag recommendation10.1016/j.inffus.2023.101862 ↗
39. Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv.
40. Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., and Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv.
41. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., AN, G., Kaiser, Ł., and Polosukhin, I. (2017, January 4–9). Attention is all you need. Proceedings of the Advances in neural information processing systems, Long Beach, CA, USA.
42. The multi-modal fusion in visual question answering: A review of attention mechanisms10.7717/peerj-cs.1400 ↗
43. Improved Blending Attention Mechanism in Visual Question Answering10.32604/csse.2023.038598 ↗
44. A Review of Vision-Based Traffic Semantic Understanding in ITSs10.1109/TITS.2022.3182410 ↗
45. (2023, June 20). Appendix—LTP4 4.1.4 Documents. Available online: https://ltp.readthedocs.io/zh_CN/latest/appendix.html.
46. Social Similarity Routing Algorithm based on Socially Aware Networks in the Big Data Environment10.1007/s11265-022-01790-3 ↗
47. Reimers, N., and Gurevych, I. (2019). Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv.10.18653/v1/D19-1410 ↗
48. (2023, June 10). CoSENT: A More Effective Sentence Vector Scheme than Sentence-BERT-Scientific Spaces. Available online: https://spaces.ac.cn/archives/8847.
49. Emotion classification for short texts: An improved multi-label method10.1057/s41599-023-01816-6 ↗
50. Rethinking Bayesian learning for data analysis: The art of prior and inference in sparsity-aware modeling10.1109/MSP.2022.3198201 ↗
51. Zhang, Y., Shao, Z., Zhang, J., Wu, B., and Zhou, L. The effect of image enhancement on influencer’s product recommendation effectiveness: The roles of perceived influencer authenticity and post type. J. Res. Interact. Mark., 2023.10.1108/JRIM-09-2022-0286 ↗
52. Wei, J., and Zou, K. (2019). Eda: Easy data augmentation techniques for boosting performance on text classification tasks. arXiv.10.18653/v1/D19-1670 ↗
53. Anaby-Tavor, A., Carmeli, B., Goldbraich, E., Kantor, A., Kour, G., Shlomov, S., Tepper, N., and Zwerdling, N. (2023, January 7–14). Do not have enough data? Deep learning to the rescue!. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA.
54. Petroni, F., Rocktäschel, T., Riedel, S., Lewis, P., Bakhtin, A., Wu, Y., and Miller, A. (2019). Language models as knowledge bases?. arXiv.10.18653/v1/D19-1250 ↗
55. Li, X.L., and Liang, P. (2021). Prefix-tuning: Optimizing continuous prompts for generation. arXiv.10.18653/v1/2021.acl-long.353 ↗
56. Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing10.1145/3560815 ↗
57. Nigh, M. (2023, June 25). ChatGPT3 Prompt Engineering. Available online: https://github.com/mattnigh/ChatGPT3-Free-Prompt-List.
58. Johnson, R., and Zhang, T. (August, January 30). Deep pyramid convolutional neural networks for text categorization. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Vancouver, BC, Canada.
59. Lai, S., Xu, L., Liu, K., and Zhao, J. (2015, January 25–30). Recurrent convolutional neural networks for text classification. Proceedings of the AAAI conference on artificial intelligence, Austin, TX, USA.10.1609/aaai.v29i1.9513 ↗