Abstract
Three critical design points: Joint learning, weak supervision, and new representations.
- Bunescu, R.C., Mooney, R.J. Learning to extract relations from the Web using minimal supervision. In Proceedings of the 45<sup>th</sup> Annual Meeting Assoc. Computational Linguistics, 2007, 576--583.Google Scholar
- Cafarella, M.J., Downey, D., Soderland, S., Etzioni, O. KnowItNow: Fast, scalable information extraction from the Web. In Proceedings of Conf. on Human Language Tech. Empirical Methods in Natural Language Processing, 2005, 563--570. Google ScholarDigital Library
- Caruana, R. Multitask learning: A knowledge-based source of inductive bias. In Proceedings of the 10<sup>th</sup> Intern. Conf. Machine Learning, 1993, 41--48. Google ScholarDigital Library
- Dong, X. et al. Knowledge Vault: A Web-scale approach to probabilistic knowledge fusion. In Proceedings of the 20<sup>th</sup> ACM SIGKDD Intern. Conf. Knowledge Discovery and Data Mining, 2014, 601--610. Google ScholarDigital Library
- Grover, A. and Leskovec, J. node2vec: Scalable feature learning for networks. In Proceedings of the 22<sup>nd</sup> ACM SIGKDD Intern. Conf. Knowledge Discovery and Data Mining, 2016, 855--864. Google ScholarDigital Library
- Hoffmann, R., Zhang, C., Ling, X., Zettlemoyer, L., Weld, D.S. Knowledge-based weak supervision for information extraction of overlapping relations. In Proceedings of the 49<sup>th</sup> Annual Meeting of the Assoc. Computational Linguistics--Human Language Technologies, 1, 2011, 541--550. Google ScholarDigital Library
- Lehmann, J. et al. DBpedia---A large-scale, multilingual knowledge base extracted from Wikipedia. Semantic Web 6, 2 (2014), 167--195.Google Scholar
- Mahdisoltani, F., Biega, J. and Suchanek, F.M. YAGO3: A knowledge base from multilingual wikipedias. In Proceedings of the 7<sup>th</sup> Biennial Conf. Innovative Data Systems Research, 2013.Google Scholar
- Mallory, E.K., Zhang, C., Ré, C. and Altman, R.B. Large-scale extraction of gene interactions from full-text literature using DeepDive. Bioinformatics 32, 1 (2015), 106--113.Google Scholar
- Mann, G.S. and McCallum, A. Generalized expectation criteria for semi-supervised learning with weakly labeled data. J. Machine Learning Research 11 (Feb 2010), 955--984. Google ScholarDigital Library
- Manning, C. Representations for language: From word embeddings to sentence meanings. Presented at Simons Institute for the Theory of Computing, UC Berkeley; https://nlp.stanford.edu/manning/talks/Simons-Institute-Manning-2017.pdf.Google Scholar
- Mikolov, T., Chen, K., Corrado, G. and Dean, J. Efficient estimation of word representations in vector space, 2013; arXiv preprint arXiv:1301.3781.Google Scholar
- Mintz, M., Bills, S., Snow, R. and Jurafsky, D. Distant supervision for relation extraction without labeled data. In Proceedings of the Joint Conf. 47<sup>th</sup> Annual Meeting of the Assoc. Computational Linguistics and the 4<sup>th</sup> Conf. Asian Federation of Natural Language Processing, 2009, 1003--1011. Google ScholarDigital Library
- Nickel, M. and Kiela, D. Poincaré embeddings for learning hierarchical representations. Advances in Neural Information Processing Systems 30 (2017), 6341--6350.Google Scholar
- Ratner, A., Bach, S., Varma, P. and Ré, C. Weak supervision: the new programming paradigm for machine learning. Hazy Research; https://hazyresearch.github.io/snorkel/blog/ws_blog_post.html.Google Scholar
- Ren, X., He, W., Qu, M., Voss, C. R., Ji, H., Han, J. Label noise reduction in entity typing by heterogeneous partial-label embedding. In Proceedings of the 22<sup>nd</sup> ACM SIGKDD Intern. Conf. Knowledge Discovery and Data Mining, (2016), 1825--1834. Google ScholarDigital Library
- Ruder, S. An overview of multi-task learning in deep neural networks, 2017; arXiv preprint arXiv: 1706.05098.Google Scholar
- Zhang, C., Ré, C., Cafarella, M., De Sa, C., Ratner, A., Shin, J., Wang, F., Wu, S. DeepDive: Declarative knowledge base construction. Commun. ACM 60, 5 (May 2017), 93--102. Google ScholarDigital Library
- Zhang, C., Shin, J., Ré, C., Cafarella, M. and Niu, F. Extracting databases from dark data with DeepDive. In Proceedings of the Intern. Conf. Management of Data, 2016, 847--859. Google ScholarDigital Library
Index Terms
- Research for practice: knowledge base construction in the machine-learning era
Recommendations
Research on simplified decoding algorithm of RA code
ICICA'11: Proceedings of the Second international conference on Information Computing and ApplicationsRA code, using BP iterative decoding algorithm for decoding in AWGN channel, is linear time encoding and decoding algorithm and its performance is closer to the Shannon limit. In order to improve decoding speed and reduce decoding complexity, this paper ...
Research: Sub-block retransmission ARQ schemes
In this paper we propose a sub-block retransmission scheme for ARQ and hybrid ARQ. When the channel is quiet the sub-block retransmission scheme behaves like a conventional ARQ or hybrid ARQ scheme. As the channel becomes increasingly noisy, the data ...
Research and Practice on the Training Mode of BIM Professional Engineers
ICEIT 2019: Proceedings of the 2019 8th International Conference on Educational and Information TechnologyThis paper focuses on how to train BIM professional engineers in civil engineering majors in applied universities of ordinary universities. In view of the current situation in China, it is proposed to develop BIM technology popularization education in ...
Comments