Abstract
Natural Answer Generation (NAG), which generates natural answer sentences for the given question, has received much attention in recent years. Compared with traditional QA systems, NAG could offer specific entities fluently and naturally, which is more user-friendly in the real world. However, existing NAG systems usually utilize simple retrieval and embedding mechanism, which is hard to tackle complex questions. They suffer issues containing knowledge insufficiency, entity ambiguity, and especially poor expressiveness during generation. To address these challenges, we propose an improved knowledge extractor to retrieve supporting graphs from the knowledge base, and an extending graph transformer to encode the supporting graph, which considers global and variable information as well as the communication path between entities. In this paper, we propose a framework called G-NAG, including a knowledge extractor, an incorporating encoder, and an LSTM generator. Experimental results on two complex QA datasets demonstrate the efficiency of G-NAG compared with state-of-the-art NAG systems and transformer baselines.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
WBMs are implemented in https://github.com/Maluuba/nlgeval.
- 3.
Since different tailoring for the dataset, the result of HM-NAG is not the same as it reported.
References
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)
Beck, D., Haffari, G., Cohn, T.: Graph-to-sequence learning using gated graph neural networks, pp. 273–283. Association for Computational Linguistics, Melbourne. https://www.aclweb.org/anthology/P18-1026
Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)
Denkowski, M., Lavie, A.: Meteor universal: language specific translation evaluation for any target language, pp. 376–380. ACL (2014)
Elsahar, H., Gravier, C., Laforest, F.: Zero-shot question generation from knowledge graphs for unseen predicates and entity types. ACL (2018)
Fu, Y., Feng, Y.: Natural answer generation with heterogeneous memory. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2018)
Gu, J., Lu, Z., Li, H., Li, V.O.: Incorporating copying mechanism in sequence-to-sequence learning. arXiv preprint arXiv:1603.06393 (2016)
Gulcehre, C., Ahn, S., Nallapati, R., Zhou, B., Bengio, Y.: Pointing the unknown words. arXiv preprint arXiv:1603.08148 (2016)
Hasibi, F., Balog, K., Bratsberg, S.E.: Dynamic factual summaries for entity cards. In: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 773–782. ACM (2017)
He, S., Liu, C., Liu, K., Zhao, J.: Generating natural answers by incorporating copying and retrieving mechanisms in sequence-to-sequence learning. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (2017)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Koncel-Kedziorski, R., Bekal, D., Luan, Y., Lapata, M., Hajishirzi, H.: Text generation from knowledge graphs with graph transformers. arXiv preprint arXiv:1904.02342 (2019)
Lin, P., Song, Q., Wu, Y.: Fact checking in knowledge graphs with ontological subgraph patterns. Data Sci. Eng. 3(4), 341–358 (2018)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)
Miller, A., Fisch, A., Dodge, J., Karimi, A.H., Bordes, A., Weston, J.: Key-value memory networks for directly reading documents. arXiv preprint arXiv:1606.03126
Mohammed, S., Shi, P., Lin, J.: Strong baselines for simple question answering over knowledge graphs with and without neural networks. In: ACL, pp. 291–296 (2018)
Nallapati, R., Zhou, B., Gulcehre, C., Xiang, B., et al.: Abstractive text summarization using sequence-to-sequence RNNS and beyond. arXiv preprint arXiv:1602.06023
Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. Association for Computational Linguistics (2002)
Reinanda, R., Meij, E., de Rijke, M.: Mining, ranking and recommending entity aspects. In: Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 263–272. ACM (2015)
See, A., Liu, P.J., Manning, C.D.: Get to the point: summarization with pointer-generator networks. arXiv preprint arXiv:1704.04368 (2017)
Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. arXiv preprint arXiv:1803.02155 (2018)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)
Wang, R., Wang, M., Liu, J., Chen, W., Cochez, M., Decker, S.: Leveraging knowledge graph embeddings for natural language question answering. In: Li, G., Yang, J., Gama, J., Natwichai, J., Tong, Y. (eds.) DASFAA 2019. LNCS, vol. 11446, pp. 659–675. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-18576-3_39
Xu, K., Wu, L., Wang, Z., Feng, Y., Witbrock, M., Sheinin, V.: Graph2seq: gEraph to sequence learning with attention-based neural networks. arXiv preprint arXiv:1804.00823 (2018)
Yin, J., Jiang, X., Lu, Z., Shang, L., Li, H., Li, X.: Neural generative question answering. arXiv preprint arXiv:1512.01337 (2015)
Zhu, J., Li, J., Zhu, M., Qian, L., Zhang, M., Zhou, G.: Modeling graph structure in transformer for better AMR-to-text generation (2019)
Acknowledgement
This work was supported by NSFC under grant 61932001 and 61961130390.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, X., Hu, S., Zou, L. (2020). Natural Answer Generation via Graph Transformer. In: Wang, X., Zhang, R., Lee, YK., Sun, L., Moon, YS. (eds) Web and Big Data. APWeb-WAIM 2020. Lecture Notes in Computer Science(), vol 12317. Springer, Cham. https://doi.org/10.1007/978-3-030-60259-8_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-60259-8_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60258-1
Online ISBN: 978-3-030-60259-8
eBook Packages: Computer ScienceComputer Science (R0)