Abstract
As one of the most important research topics in the field of natural language processing, open information extraction has achieved gratifying research findings in recent years. Even if so much effort is put into the work of open information extraction, there are still many shortcomings and great room for improvement in the existing system. The traditional open information extraction task relies heavily on the artificially defined extraction paradigm, and it will produce error accumulation and propagation. The end-to-end model relies on a large number of training data, and it is hard to re-train with the increase of the model. To cope with the difficulty of updating parameters of large neural network models, in this paper, we propose a solution based on the meta-learning framework, we design a neural network-based converter module, which effectively combines the learned model parameters with the new model parameters. Then update the parameters of the original open information extraction model using the parameters calculated by the converter. This can not only avoid the problem of error propagation of traditional models but also effectively deal with the iterative updating of open information extraction models. We employ a large and public Open IE benchmark to demonstrate the performance of our approach. The experimental results show that our model can achieve better performance than existing baselines, and compared with the re-training model, our strategy can not only greatly shorten the update time of the model, but also not lose the performance of the model completely re-trained with all the training data.
Similar content being viewed by others
Availability of data and material
The experimental data we use, including the experimental test data, are open and transparent.
Code availability
The code for the experiment will be uploaded to Github later
Notes
References
Angeli G, Premkumar MJJ, Manning CD (2015) Leveraging linguistic structure for open domain information extraction. pp 344–354
Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473
Binici K, Pham NT, Mitra T, Leman K (2021) Preventing catastrophic forgetting and distribution mismatch in knowledge distillation via synthetic data. CoRR arXiv: abs/2108.05698
Cetto M, Niklaus C, Freitas A, Handschuh, S (2018) Graphene, (1807.11276.) Semantically-linked propositions in open information extraction
Chong Y, Peng C, Zhang C, Wang Y, Feng W, Pan S (2021) Learning domain invariant and specific representation for cross-domain person re-identification. Appl Intell 51(8):5219–5232. https://doi.org/10.1007/s10489-020-02107-2
Christensen J, Mausam Soderland S, Etzioni O (2010) Semantic role labeling for open information extraction. In: Proceedings of the NAACL HLT 2010 first international workshop on formalisms and methodology for learning by reading, FAM-LbR ’10, pp 52–60. Association for Computational Linguistics, USA
Cui L, Wei F, Zhou M (2018) Neural open information extraction. In: Gurevych I, Miyao Y (eds.) Proceedings of the 56th annual meeting of the association for computational linguistics, ACL 2018, Melbourne, Australia, 15–20 July 2018, vol 2: Short Papers, pp 407–413. Association for Computational Linguistics (2018). https://doi.org/10.18653/v1/P18-2065
Del Corro L, Gemulla R (2013) Clausie: clause-based open information extraction. pp 355–366
Diaz-Aviles E, Drumond L, Schmidt-Thieme L, Nejdl W (2012) Real-time top-n recommendation in social streams. In: Cunningham P, Hurley NJ, Guy I, Anand SS (eds) Sixth ACM conference on recommender systems, RecSys ’12, Dublin, Ireland, 9–13 Sept 2012, pp.59–66. ACM . https://doi.org/10.1145/2365952.2365968
Etzioni O, Banko M, Soderland S, Weld DS (2008) Open information extraction from the web. Commun ACM 51(12):68–74
Etzioni O, Fader A, Christensen J, Soderland S, Mausam M (2011). Open information extraction: the second generation, vol IJCAI’11. AAAI Press, pp 3–10
Fader A, Soderland S, Etzioni O (2011) Identifying relations for open information extraction. pp 1535–1545
Feng Y, Chen J, Yang Z, Song X, Chang Y, He S, Xu E, Zhou Z (2021) Similarity-based meta-learning network with adversarial domain adaptation for cross-domain fault identification. Knowl Based Syst 217:106829. https://doi.org/10.1016/j.knosys.2021.106829
Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: Precup D, Teh YW (eds) Proceedings of the 34th international conference on machine learning, ICML 2017, Sydney, NSW, Australia, Aug 6–11 2017, Proceedings of Machine Learning Research, vol 70, pp 1126–1135. PMLR.http://proceedings.mlr.press/v70/finn17a.html
Ganin Y, Ustinova E, Ajakan H, Germain P, Larochelle H, Laviolette F, Marchand M, Lempitsky VS (2016) Domain-adversarial training of neural networks. J Mach Learn Res 17:17:59:1-59:35 http://jmlr.org/papers/v17/15-239.html
Gashteovski K, Gemulla R, Corro LD (2017) Minie: minimizing facts in open information extraction. In: Palmer M, Hwa R, Riedel S (eds) Proceedings of the 2017 conference on empirical methods in natural language processing, EMNLP 2017, Copenhagen, Denmark, 9–11 Sept 2017, pp 2630–2640. Association for Computational Linguistics (2017). https://doi.org/10.18653/v1/d17-1278
Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville AC, Bengio Y (2014) Generative adversarial nets. In: Ghahramani Z, Welling M, Cortes C, Lawrence, Weinberger KQ (eds) Advances in neural information processing systems 27: annual conference on neural information processing systems 2014, 8–13 Dec 2014, Montreal, Quebec, Canada, pp 2672–2680. https://proceedings.neurips.cc/paper/2014/hash/5ca3e9b122f61f8f06494c97b1afccf3-Abstract.html
Han J, Wang H (2021) Improving open information extraction with distant supervision learning. Neural Process Lett, pp 1–20
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Hoffman J, Tzeng E, Donahue J, Jia Y, Saenko K, Darrell T(2014) One-shot adaptation of supervised deep convolutional models. In: Bengio Y, LeCun Y (eds) 2nd International conference on learning representations, ICLR 2014, Banff, AB, Canada, 14–16 Apr 2014, Workshop Track Proceedings . arXiv: org/abs/1312.6204
Huang H, Liu Q (2021) Domain structure-based transfer learning for cross-domain word representation. Inf Fusion 76:145–156. https://doi.org/10.1016/j.inffus.2021.05.013
Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Bach FR, Blei DM (eds) Proceedings of the 32nd international conference on machine learning, ICML 2015, Lille, France, 6–11 July 2015, JMLR workshop and conference proceedings, vol 37, pp 448–456. JMLR.org (2015). http://proceedings.mlr.press/v37/ioffe15.html
Liu M, Tuzel O (2016). Coupled generative adversarial networks. In: Lee DD, Sugiyama M, von Luxburg U, Guyon I, Garnett R (eds.) Advances in neural information processing systems 29: annual conference on neural information processing systems 2016, 5–10 Dec 2016, Barcelona, Spain, pp 469–477 https://proceedings.neurips.cc/paper/2016/hash/502e4a16930e414107ee22b6198c578f-Abstract.html
Madan A, Prasad, R.: B-small, (2021). A bayesian neural network approach to sparse model-agnostic meta-learning. IEEE, pp 2730–2734. https://doi.org/10.1109/ICASSP39728.2021.9414437
Mausam Schmitz M, Soderland S, Bart R, Etzioni O (2012) Open language learning for information extraction. In: Proceedings of the 2012 joint conference on empirical methods in natural language processing and computational natural language learning, pp 523–534. Association for Computational Linguistics, Jeju Island, Korea . https://www.aclweb.org/anthology/D12-1048
Mausam M (2016) Open information extraction systems and downstream applications. In: Proceedings of the twenty-fifth international joint conference on artificial intelligence, pp 4074–4077
Otter DW, Medina JR, Kalita JK (2021) A survey of the usages of deep learning for natural language processing. IEEE Trans Neural Networks Learn Syst 32(2):604–624. https://doi.org/10.1109/TNNLS.2020.2979670
Mausam Pal H (2016) Demonyms and compound relational nouns in nominal open IE. In: Proceedings of the 5th workshop on automated knowledge base construction, pp 35–39. Association for Computational Linguistics, San Diego, CA. https://doi.org/10.18653/v1/W16-1307
Pascanu R, Mikolov T, Bengio Y (2013) On the difficulty of training recurrent neural networks. In: Proceedings of the 30th international conference on machine learning, ICML 2013, Atlanta, GA, USA, 16–21 June 2013, JMLR workshop and conference proceedings, vol 28, pp 1310–1318. JMLR.org . http://proceedings.mlr.press/v28/pascanu13.html
Patterson DA, Gonzalez J, Le QV, Liang C, Munguia L, Rothchild D, So DR, Texier M, Dean J (2021) Carbon emissions and large neural network training. CoRR arXiv: abs/2104.10350
Saha S, Pal H Mausam (2017) Bootstrapping for numerical open IE. In: Proceedings of the 55th annual meeting of the association for computational linguistics (vol 2: Short Papers), pp 317–323. Association for Computational Linguistics, Vancouver, Canada . https://doi.org/10.18653/v1/P17-2050
Schneider R, Oberhauser T, Klatt T, Gers FA, Löser, A (2017) Analysing errors of open information extraction systems. arXiv preprint arXiv:1707.07499
Stanovsky G, Dagan I (2016) Creating a large benchmark for open information extraction. pp 2300–2305
Stanovsky G, Ficler J, Dagan I, Goldberg Y (2016) Getting more out of syntax with props. arXiv preprint arXiv:1603.01648
Stanovsky G, Michael J, Zettlemoyer L, Dagan I (2018) Supervised open information extraction. In: Walker MA, Ji H, Stent A (eds) Proceedings of the 2018 conference of the north american chapter of the association for computational linguistics: human language technologies, NAACL-HLT 2018, New Orleans, Louisiana, USA, 1–6 June 2018, vol 1 (Long Papers), pp 885–895. Association for Computational Linguistics . https://doi.org/10.18653/v1/n18-1081
Sun J, Li Y, Chen H, Peng Y, Zhu J (2021) Unsupervised cross domain person re-identification by multi-loss optimization learning. IEEE Trans Image Process 30:2935–2946. https://doi.org/10.1109/TIP.2021.3056889
Triantafillou E, Zhu T, Dumoulin V, Lamblin P, Evci U, Xu K, Goroshin R, Gelada C, Swersky K, Manzagol P, Larochelle H, (2020) Meta-dataset, (2020. OpenReview.net (2020).) In: Addis A, April E (eds) A dataset of datasets for learning to learn from few examples, pp 26–30 https://openreview.net/forum?id=rkgAGAVKPr
Tzeng E, Hoffman J, Saenko K, Darrell T (2017). Adversarial discriminative domain adaptation. IEEE Comput Soc, pp 2962–2971. https://doi.org/10.1109/CVPR.2017.316
Wingfield A, Stine-Morrow EA (2000) Language and speech. The Handbook of Aging And Cognition. pp 359–416
Wu F, Weld DS (2010) Open information extraction using wikipedia. pp 118–127
Yates A, Banko M, Broadhead M, Cafarella MJ, Etzioni O, Soderland S (2007) Textrunner: open information extraction on the web. pp 25–26
Yin M, Tucker G, Zhou M, Levine S, Finn C (2020) Meta-learning without memorization. In: Addis A, April E (eds). pp 26–30. OpenReview.net (2020). https://openreview.net/forum?id=BklEFpEYwS
Yu T, Quillen D, He Z, Julian R, Hausman K, Finn C, Levine S (2019). Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning. In: Kaelbling LP, Kragic D, Sugiura K (eds.) 3rd Annual conference on robot learning, CoRL 2019, Osaka, Japan, 30 Oct–1 Nov 2019, Proceedings, Proceedings of machine learning research, vol 100, pp 1094–1100. PMLR http://proceedings.mlr.press/v100/yu20a.html
Zhang Y, Feng F, Wang C, He X, Wang M, Li Y, Zhang Y (2020) How to retrain recommender system?: A sequential meta-learning method. In: Huang J, Chang Y, Cheng X, Kamps J, Murdock V, Wen J, Liu Y (eds) Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval, SIGIR 2020, Virtual Event, China, 25–30 July 2020, pp 1479–1488. ACM . https://doi.org/10.1145/3397271.3401167
Funding
This paper was partially supported by NSFC grant U1866602, 61772157.
Author information
Authors and Affiliations
Contributions
JH is responsible for this paper design and experimentation and partial writing. HW is responsible for the writing and review of the paper.
Corresponding author
Ethics declarations
Conflict of interest
We declare that we have no known competing financial interests or personal relationsships that could have appeared to influence the work reported in this paper.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Han, J., Wang, H. A meta learning approach for open information extraction. Neural Comput & Applic 34, 12681–12694 (2022). https://doi.org/10.1007/s00521-022-07114-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-022-07114-7