Abstract
Complex Question Answering (CQA) over Knowledge Base (KB) involves transferring natural language questions to a sequence of actions, which are utilized to fetch entities and relations for final answer. Typically, meta-learning based models regard question types as standards to divide dataset for pseudo-tasks. However, question type, manually labeled in CQA data set, is indispensable as a filter in the support set retrieving phase, which raises two main problems. First, preset question types could mislead the model to be confined to a non-optimal search space for meta-learning. Second, the annotation dependency makes it difficult to migrate to other datasets. This paper introduces a novel architecture to alleviate above issues by using a co-training scheme featured with self-supervised mechanism for model initialization. Our method utilizes a meta-learning classifier instead of pre-labeled tags to find the optimized search space. Experiments in this paper show that our model achieves state-of-the-art performance on CQA dataset without encoding question type.
Supported by Lenovo Research.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Ansari, GA., Saha, A., Kumar, V., Bhambhani, M., Sankaranarayanan, K., Chakrabarti, S.: Neural program induction for KBQA without gold programs or query annotations. In: IJCAI, pp. 4890–4896 (2019)
Berant, J., Chou, A., Frostig, R., Liang, P.: Semantic parsing on freebase from question-answer pairs. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1533–1544 (October 2013). https://aclanthology.org/D13-1160
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, pp. 1126–1135. PMLR (2017)
Guo, D., Tang, D., Duan, N., Zhou, M., Yin, J.: Dialog-to-action: conversational question answering over a large-scale knowledge base. In: Advances in Neural Information Processing Systems, pp. 2942–2951 (2018)
Guu, K., Pasupat, P., Liu, E.Z., Liang, P.: From language to programs: bridging reinforcement learning and maximum marginal likelihood. arXiv preprint arXiv:1704.07926 (2017)
Hua, Y., Li, Y.F., Haffari, G., Qi, G., Wu, W.: Retrieve, program, repeat: complex knowledge base question answering via alternate meta-learning. arXiv preprint arXiv:2010.15875 (2020)
Huang, P.S., He, X., Gao, J., Deng, L., Acero, A., Heck, L.: Learning deep structured semantic models for web search using clickthrough data. In: Proceedings of the 22nd ACM international conference on Information & Knowledge Management, pp. 2333–2338 (2013)
Huang, P.S., Wang, C., Singh, R., Yih, W., He, X.: Natural language to structured query generation via meta-learning. arXiv preprint arXiv:1803.02400 (2018)
Jin, H., Li, C., Zhang, J., Hou, L., Li, J., Zhang, P.: XLORE2: large-scale cross-lingual knowledge graph construction and application. Data Intell. 1(1), 77–98 (2019)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Luo, L., Xiong, Y., Liu, Y., Sun, X.: Adaptive gradient methods with dynamic bound of learning rate. arXiv preprint arXiv:1902.09843 (2019)
Macqueen, J.: Some methods for classification and analysis of multivariate observations. In: 5th Berkeley Symposium on Mathematical Statistics and Probability, pp. 281–297 (1967)
Nichol, A., Schulman, J.: Reptile: a scalable metalearning algorithm. arXiv preprint arXiv:1803.02999 2(3), 4 (2018)
Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)
Saha, A., Ansari, G.A., Laddha, A., Sankaranarayanan, K., Chakrabarti, S.: Complex program induction for querying knowledge bases in the absence of gold programs. Trans. Assoc. Comput. Linguist. 7, 185–200 (2019)
Saha, A., Pahuja, V., Khapra, M.M., Sankaranarayanan, K., Chandar, S.: Complex sequential question answering: towards learning to converse over linked question answer pairs with a knowledge graph. In: 32nd AAAI Conference on Artificial Intelligence (2018)
Shen, T., et al.: Multi-task learning for conversational question answering over a large-scale knowledge base. arXiv preprint arXiv:1910.05069 (2019)
Sutton, R.S., McAllester, D.A., Singh, S.P., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems, pp. 1057–1063 (2000)
Vrandečić, D., Krötzsch, M.: Wikidata: a free collaborative knowledgebase. Commun. ACM 57(10), 78–85 (2014)
Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3), 229–256 (1992)
Yih, W., He, X., Meek, C.: Semantic parsing for single-relation question answering. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 643–648 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, B., Liu, L., Wang, P. (2022). Few-Shot Learning with Self-supervised Classifier for Complex Knowledge Base Question Answering. In: Memmi, G., Yang, B., Kong, L., Zhang, T., Qiu, M. (eds) Knowledge Science, Engineering and Management. KSEM 2022. Lecture Notes in Computer Science(), vol 13369. Springer, Cham. https://doi.org/10.1007/978-3-031-10986-7_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-10986-7_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-10985-0
Online ISBN: 978-3-031-10986-7
eBook Packages: Computer ScienceComputer Science (R0)