ISSN 2071-8594

Российская академия наук

 

А. О. Шелманов, Д. А. Девяткин, В. А. Исаков, И. В. Смирнов Открытое извлечение информации из текстов Часть II. Извлечения семантических отношений с помощью машинного обучения без учителя

Аннотация.

Работа посвящена «открытому извлечению информации» из текстов на естественном языке (open information extraction). Описывается подход к решению задачи извлечения семантических отношений из текстов на основе машинного обучения без учителя. Подход основан на методах глубокой кластеризации (deep clustering), в которых алгоритм кластеризации интегрирован внутрь многослойного нейросетевого автокодировщика. Эта модель применяется для объединения в группы поверхностных связей (триплетов), которые можно интерпретировать как семантические отношения. Представлен метод для извлечения терминов и поверхностных связей на основе правил и статистических данных.

Ключевые слова:

открытое извлечение информации, семантические отношения, машинное обучение без учителя, нейронные сети, автокодировщик.

Стр. 39-49.

DOI 10.14357/20718594190204

Полная версия статьи в формате pdf.

Литература

1. Open information extraction from the web. / Michele Banko, Michael J Cafarella, Stephen Soderland et al. // IJCAI. — Vol. 7. — 2007. — P. 2670–2676.
2. Textrunner: open information extraction on the web / Alexander Yates, Michael Cafarella, Michele Banko et al. // Proceedings of Human Language Technologies: The Annual Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations / Association for Computational Linguistics. — 2007. — P. 25–26.
3. Wu F., Weld D. S. Open information extraction using wikipedia // Proceedings of the 48th annual meeting of the association for computational linguistics / Association for Computational Linguistics. — 2010. — P. 118–127.
4. Fader A., Soderland S., Etzioni O. Identifying relations for open information extraction // Proceedings of the conference on empirical methods in natural language processing / Association for Computational Linguistics. — 2011. — P. 1535–1545.
5. Open information extraction: The second generation. / Oren Etzioni, Anthony Fader, Janara Christensen et al. // IJCAI. — Vol. 11. — 2011. — P. 3–10.
6. Открытое извлечение информации из текстов. Часть 1. Постановка задачи и обзор методов / А.О. Шелманов, В.А. Исаков, М.А. Станкевич, И.В. Смирнов // Искусственный интеллект и принятие решений. — 2018. — № 2. — С. 47–61.
7. Lin D., Pantel P. Discovery of inference rules for question-answering // Natural Language Engineering. — 2001. — Vol. 7, no. 4. — P. 343–360.
8. Takase S., Okazaki N., Inui K. Fast and large-scale unsupervised relation extraction // Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation. — 2015. — P. 96–105.
9. Distributed representations of words and phrases and their compositionality / Tomas Mikolov, Ilya Sutskever, Kai Chen et al. // Advances in neural information processing systems. — 2013. — P. 3111–3119.
10. Structured relation discovery using generative models / Limin Yao, Aria Haghighi, Sebastian Riedel, Andrew McCallum // Proceedings of the Conference on Empirical Methods in Natural Language Processing / Association for Computational Linguistics. — 2011. — P. 1456–1466.
11. Blei D. M., Ng A. Y., Jordan M. I. Latent dirichlet allocation // Journal of machine Learning research. — 2003. — Vol. 3, no. Jan. — P. 993–1022.
12. Yao L., Riedel S., McCallum A. Unsupervised relation discovery with sense disambiguation // Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers-Volume 1 / Association for Computational Linguistics. — 2012. — P. 712–720.
13. De Lacalle O. L., Lapata M. Unsupervised relation extraction with general domain knowledge // Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. — 2013. — P. 415–425.
14. A framework for incorporating general domain knowledge into latent dirichlet allocation using first-order logic / David Andrzejewski, Xiaojin Zhu, Mark Craven, Benjamin Recht // IJCAI Proceedings-International Joint Conference on Artificial Intelligence. — Vol. 22. — 2011. — P. 1171.
15. Marcheggiani D., Titov I. Discrete-state variational autoencoders for joint discovery and factorization of relations // Transactions of the Association for Computational Linguistics. — 2016. — Vol. 4. — P. 231–244.
16. Kingma D. P., Welling M. Auto-encoding variational bayes // arXiv preprint arXiv:1312.6114. — 2013.
17. Hasegawa T., Sekine S., Grishman R. Discovering relations among named entities from large corpora // Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics / Association for Computational Linguistics. — 2004. — P. 415.
18. Shinyama Y., Sekine S. Preemptive information extraction using unrestricted relation discovery // Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics / Association for Computational Linguistics. — 2006. — P. 304–311.
19. Unsupervised relation extraction by mining wikipedia texts using information from the web / Yulan Yan, Naoaki Okazaki, Yutaka Matsuo et al. // Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2-Volume 2 / Association for Computational Linguistics. — 2009. — P. 1021–1029.
20. Xie J., Girshick R., Farhadi A. Unsupervised deep embedding for clustering analysis // International conference on machine learning. — 2016. — P. 478–487.
21. Deep clustering with convolutional autoencoders / Xifeng Guo, Xinwang Liu, En Zhu, Jianping Yin // International Conference on Neural Information Processing / Springer. — 2017. — P. 373–382.
22. Tian K., Zhou S., Guan J. Deepcluster: A general clustering framework based on deep learning // Joint European Conference on Machine Learning and Knowledge Discovery in Databases / Springer. — 2017. — P. 809–825.
23. Learning deep representations for graph clustering. / Fei Tian, Bin Gao, Qing Cui et al. // AAAI. — 2014. — P. 1293–1299.
24. Auto-encoder based data clustering / Chunfeng Song, Feng Liu, Yongzhen Huang et al. // Iberoamerican Congress on Pattern Recognition / Springer. — 2013. — P. 117–124.
25. Hinton G. E., Salakhutdinov R. R. Reducing the dimensionality of data with neural networks // science. — 2006. — Vol. 313, no. 5786. — P. 504–507.
26. Frantzi K., Ananiadou S., Mima H. Automatic recognition of multi-word terms:. the c-value/nc-value method // International journal on digital libraries. — 2000. — Vol. 3, no. 2. — P. 115–130.
27. Семантико-синтаксический анализ естественных языков. Часть II. Метод семантико-синтаксического анализа текстов / И. В. Смирнов, А. О. Шелманов, Е. С. Кузнецова, И. В. Храмоин // Искусственный интеллект и принятие решений. — 2014. — № 1. — С. 11–24.
28. Kutuzov A., Kuzmenko E. Webvectors: a toolkit for building web interfaces for vector semantic models // International Conference on Analysis of Images, Social Networks and Texts / Springer. — 2016. — P. 155–161.
29. Lang J., Lapata M. Unsupervised semantic role induction via split-merge clustering // Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies / Association for Computational Linguistics. — 2011. — P. 1117–1126.
30. Titov I., Khoddam E. Unsupervised induction of semantic roles within a reconstruction-error minimization framework // Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. — 2015. — P. 1–10.