research-article

Open access

Never-ending learning

Communications of the ACM, Volume 61, Issue 5

Pages 103 - 115

https://doi.org/10.1145/3191513

Published: 24 April 2018 Publication History

All formats PDF

Abstract

Whereas people learn many different types of knowledge from diverse experiences over many years, and become better learners over time, most current machine learning systems are much more narrow, learning just a single function or data model based on statistical analysis of a single data set. We suggest that people learn better than computers precisely because of this difference, and we suggest a key direction for machine learning research is to develop software architectures that enable intelligent agents to also learn many types of knowledge, continuously over many years, and to become better learners over time. In this paper we define more precisely this never-ending learning paradigm for machine learning, and we present one case study: the Never-Ending Language Learner (NELL), which achieves a number of the desired properties of a never-ending learner. NELL has been learning to read the Web 24hrs/day since January 2010, and so far has acquired a knowledge base with 120mn diverse, confidence-weighted beliefs (e.g., servedWith(tea,biscuits)), while learning thousands of interrelated functions that continually improve its reading competence over time. NELL has also learned to reason over its knowledge base to infer new beliefs it has not yet read from those it has, and NELL is inventing new relational predicates to extend the ontology it uses to represent beliefs. We describe the design of NELL, experimental results illustrating its behavior, and discuss both its successes and shortcomings as a case study in never-ending learning. NELL can be tracked online at http://rtw.ml.cmu.edu, and followed on Twitter at @CMUNELL.

References

[1]

Balcan, M.-F., Blum, A. A PAC-style model for learning from labeled and unlabeled data. Proc. of COLT (2004).

Digital Library

[2]

Bengio, Y. Learning deep architectures for AI. Foundations and Trends in Machine Learning 2, 1 (2009), 1--127.

Digital Library

[3]

Bengio, Y., Louradour, J., Collobert, R., Weston, J. Curriculum learning. In Proceedings of the 26th annual international conference on machine learning (2009), ACM, 41--48.

Digital Library

[4]

Blum, A., Mitchell, T. Combining labeled and unlabeled data with co-training. Proc. of COLT (1998).

Digital Library

[5]

Brunskill, E., Leffler, B., Li, L., Littman, M.L., Roy, N. Corl: A continuous-state offset-dynamics reinforcement learner. In Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence (UAI) (2012), 53--61.

Digital Library

[6]

Callan, J. Clueweb12 data set (2013; http://lemurproject.org/clueweb12/.

[7]

Callan, J., Hoy, M. Clueweb09 data set (2009) http://boston.lti.cs.cmu.edu/Data/clueweb09/.

[8]

Carlson, A., Betteridge, J., Kisiel, B., Settles, B., Hruschka Jr, E.R., Mitchell, T.M. Toward an architecture for never-ending language learning. AAAI 5, 3 (2010a).

Digital Library

[9]

Carlson, A., Betteridge, J., Wang, R.C., Hruschka Jr., E.R., Mitchell, T.M. Coupled semi-supervised learning for information extraction. Proc. of WSDM (2010b).

Digital Library

[10]

Caruana, R. Multitask learning. Machine Learning 28 (1997), 41--75.

Digital Library

[11]

Chen, Z., Liu, B. Lifelong machine learning. Synthesis Lectures on Artificial Intelligence and Machine Learning 10, 3 (2016), 1--145.

Digital Library

[12]

Chen, X., Shrivastava, A., Gupta, A. Neil: Extracting visual knowledge from web data. In Proceedings of ICCV (2013).

Digital Library

[13]

Craven, M., DiPasquo, D., Freitag, D., McCallum, A., Mitchell, T., Nigam, K., Slattery, S. Learning to extract symbolic knowledge from the world wide web. In Proceedings of the 15th National Conference on Artificial Intelligence (1998).

Digital Library

[14]

Dempster, A., Laird, N., Rubin, D. Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. Series B (1977).

[15]

Donmez, P., Carbonell, J.G. Proactive learning: cost-sensitive active learning with multiple imperfect oracles. In Proceedings of the 17th ACM conference on Information and knowledge management (2008), ACM, 619--628.

Digital Library

[16]

Duarte, M.C., Hruschka Jr., E.R. How to read the web in portuguese using the never-ending language learner's principles. In Intelligent Systems Design and Applications (ISDA), 2014 14th International Conference on (2014), IEEE, 162--167.

[17]

Etzioni, O.e.a. Web-scale information extraction in knowitall (preliminary results). In WWW (2004).

Digital Library

[18]

Etzioni, O.e.a. Open information extraction: The second generation. Proc. of IJCAI (2011).

Digital Library

[19]

Gardner, M., Talukdar, P., Krishnamurthy, J., Mitchell, T. Incorporating vector space similarity in random walk inference over knowledge bases. Proc. of EMNLP (2014).

[20]

Krishnamurthy, J., Mitchell, T.M. Which noun phrases denote which concepts. Proc. of ACL (2011).

Digital Library

[21]

Laird, J., Newell, A., Rosenbloom, P. SOAR: An architecture for general intelligence. Artif. Intel. 33, (1987), 1--64.

Digital Library

[22]

Langley, P., McKusick, K.B., Allen, J.A., Iba, W.F., Thompson, K. A design for the ICARUS architecture. SIGART Bull. 2, 4 (1991), 104--109.

Digital Library

[23]

Lao, N., Mitchell, T., Cohen, W.W. Random walk inference and learning in a large scale knowledge base. Proc. of EMNLP (2011).

Digital Library

[24]

Lenat, D.B. Eurisko: A program that learns new heuristics and domain concepts. Artif. Intel. 21, 1--2 (1983), 61--98.

Digital Library

[25]

Maaten, L.v.d., Hinton, G. Visualizing data using t-SNE. J. Machine Learning Res. 9, Nov (2008):2579--2605.

[26]

Mitchell, T.M., Allen, J., Chalasani, P., Cheng, J., Etzioni, O., Ringuette, M.N., Schlimmer, J.C. THEO: A framework for self-improving systems. Arch. for Intel. (1991), 323--356.

[27]

Mitchell, T., Cohen, W., Hruschka, E., Talukdar, P., Betteridge, J., Carlson, A., Dalvi, B., Gardner, M., Kisiel, B., Krishnamurthy, J., Lao, N., Mazaitis, K., Mohamed, T., Nakashole, N., Platanios, E., Ritter, A., Samadi, M., Settles, B., Wang, R., Wijaya, D., Gupta, A., Chen, X., Saparov, A., Greaves, M., Welling, J. Never-ending learning. In AAAI Conference on Artificial Intelligence (2015), AAAI, 2302--2310.

Digital Library

[28]

Mohamed, T., Hruschka Jr., E.R., Mitchell, T.M. Discovering relations between noun categories. In Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing (2011), Association for Computational Linguistics, Edinburgh, Scotland, UK, 1447--1455.

Digital Library

[29]

Muggleton, S., Buntine, W. Machine invention of first-order predicates by inverting resolution. Inductivelogic programming (1992), 261--280.

[30]

Nigam, K., McCallum, A., Thrun, S., Mitchell, T. Text classification using labeled and unlabeled documents. Machine Learning 39 (2000), 103--134.

Digital Library

[31]

Pedro, S.D., Hruschka Jr, E.R. Conversing learning: Active learning and active social interaction for human supervision in never-ending learning systems. In Advances in Artificial Intelligence--IBERAMIA 2012 (Springer, 2012), 231--240.

[32]

Platanios, E.A., Blum, A., Mitchell, T.M. Estimating Accuracy from Unlabeled Data. Proc. of UAI (2014).

Digital Library

[33]

Platanios, E.A., Dubey, A., Mitchell, T.M. Estimating Accuracy from Unlabeled Data: A Bayesian Approach. In Proceedings of the International Conference on Machine Learning (2016).

Digital Library

[34]

Platanios, E.A., Poon, H., Mitchell, T.M., Horvitz, E. Estimating Accuracy from Unlabeled Data: A Probabilistic Logic Approach (2017). preprint, https://arxiv.org/abs/1705.07086.

[35]

Pujara, J., Miao, H., Getoor, L., Cohen, W. Knowledge graph identification. ISWC (2013).

Digital Library

[36]

Samadi, M., Veloso, M.M., Blum, M. Openeval: Web information query evaluation. In AAAI (2013).

Digital Library

[37]

Suchanek, F.M., Kasneci, G., Weikum, G. Yago: A Core of Semantic Knowledge. In 16th international World Wide Web conference (WWW 2007) (2007), ACM Press, New York, NY, USA.

Digital Library

[38]

Thrun, S., Mitchell, T. Lifelong robot learning. Rob. Auton. Sys. 15, (1995), 25--46.

[39]

Thrun, S., Pratt, L. (eds) Learning to learn, Kluwer Academic Publishers, Norwell, MA, USA, 1998.

Digital Library

[40]

Tong, S., Koller, D. Active learning for structure in bayesian networks. IJCAI (2001).

Digital Library

[41]

Wang, R.C., Cohen, W.W. Language-independent set expansion of named entities using the web. Proc. of ICDM (2007).

Digital Library

[42]

Wieting, J., Bansal, M., Gimpel, K., Livescu, K. Towards universal paraphrastic sentence embeddings. In Proceedings of the International Conference on Learning Representations (ICLR) (2015).

[43]

Wijaya, D.T. VerbKB: A Knowledge Base of Verbs for Natural Language Understanding. Ph.D. Dissertation, Carnegie Mellon University, 2016.

[44]

Yang, B., Mitchell, T. Leveraging knowledge bases in lstms for improving machine reading. ACL (2017).

Cited By

Da Costa LMelchiades MGirelli VColombelli FAraújo DRigo SRamos GDa Costa CRighi RBarbosa J(2024)Advancing Chatbot Conversations: A Review of Knowledge Update ApproachesJournal of the Brazilian Computer Society10.5753/jbcs.2024.288230:1(55-68)Online publication date: 25-Apr-2024
https://doi.org/10.5753/jbcs.2024.2882
Shen QQu A(2024)CosUKG: A Representation Learning Framework for Uncertain Knowledge GraphsMathematics10.3390/math1210141912:10(1419)Online publication date: 7-May-2024
https://doi.org/10.3390/math12101419
Yang BLi S(2024)UIGuider: Detecting Implicit Design Guidelines Using a Domain Knowledge Graph ApproachElectronics10.3390/electronics1307121013:7(1210)Online publication date: 26-Mar-2024
https://doi.org/10.3390/electronics13071210
Show More Cited By

Index Terms

Never-ending learning
1. Computing methodologies
  1. Artificial intelligence
  2. Machine learning
2. Theory of computation
  1. Theory and algorithms for application domains
    1. Machine learning theory

Recommendations

Never-ending learning
AAAI'15: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence

Whereas people learn many different types of knowledge from diverse experiences over many years, most current machine learning systems acquire just a single function or data model from just a single data set. We propose a never-ending learning paradigm ...
Never ending learning
ECAI'12: Proceedings of the 20th European Conference on Artificial Intelligence

We will never really understand learning or intelligence until we can build machines that learn many different things, over years, and become better learners over time.

This talk describes our research to build a Never-Ending Language Learner (NELL) ...
Conversing Learning: Active Learning and Active Social Interaction for Human Supervision in Never-Ending Learning Systems
Advances in Artificial Intelligence – IBERAMIA 2012
Abstract
The Machine Learning community have been introduced to NELL (Never-Ending Language Learning), a system able to learn from web and to use its knowledge to keep learning infinitely. The idea of continuously learning from the web brings concerns ...

Comments

Information & Contributors

Information

Published In

cover image Communications of the ACM

Communications of the ACM Volume 61, Issue 5

May 2018

104 pages

ISSN:0001-0782

EISSN:1557-7317

DOI:10.1145/3210350

Editor:
Andrew A. Chien
Association for Computing Machinery, New York, NY

Issue’s Table of Contents

Copyright © 2018 Owner/Author.

This work is licensed under a Creative Commons Attribution International 4.0 License.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 24 April 2018

Published in CACM Volume 61, Issue 5

Check for updates

Qualifiers

Research-article
Research
Refereed

Funding Sources

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

325
Total Citations
View Citations
36,566
Total Downloads

Downloads (Last 12 months)5,138
Downloads (Last 6 weeks)175

Reflects downloads up to 01 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Da Costa LMelchiades MGirelli VColombelli FAraújo DRigo SRamos GDa Costa CRighi RBarbosa J(2024)Advancing Chatbot Conversations: A Review of Knowledge Update ApproachesJournal of the Brazilian Computer Society10.5753/jbcs.2024.288230:1(55-68)Online publication date: 25-Apr-2024
https://doi.org/10.5753/jbcs.2024.2882
Shen QQu A(2024)CosUKG: A Representation Learning Framework for Uncertain Knowledge GraphsMathematics10.3390/math1210141912:10(1419)Online publication date: 7-May-2024
https://doi.org/10.3390/math12101419
Yang BLi S(2024)UIGuider: Detecting Implicit Design Guidelines Using a Domain Knowledge Graph ApproachElectronics10.3390/electronics1307121013:7(1210)Online publication date: 26-Mar-2024
https://doi.org/10.3390/electronics13071210
Pinna FHayashi VNéto JMarquesone RDuarte MOkada RRuggiero W(2024)A Modular Framework for Domain-Specific Conversational Systems Powered by Never-Ending LearningApplied Sciences10.3390/app1404158514:4(1585)Online publication date: 16-Feb-2024
https://doi.org/10.3390/app14041585
Tian XMeng Y(2024)PDEC: A Framework for Improving Knowledge Graph Reasoning Performance through Predicate DecompositionAlgorithms10.3390/a1703012917:3(129)Online publication date: 21-Mar-2024
https://doi.org/10.3390/a17030129
Sandini GSciutti AMorasso P(2024)Artificial cognition vs. artificial intelligence for next-generation autonomous robotic agentsFrontiers in Computational Neuroscience10.3389/fncom.2024.134940818Online publication date: 22-Mar-2024
https://doi.org/10.3389/fncom.2024.1349408
Han YLu GZhang SZhang LZou CWen G(2024)A Temporal Knowledge Graph Embedding Model Based on Variable TranslationTsinghua Science and Technology10.26599/TST.2023.901014229:5(1554-1565)Online publication date: Oct-2024
https://doi.org/10.26599/TST.2023.9010142
Chen CWang KLi PSakurai K(2024)A Multi-Head Federated Continual Learning Approach for Improved Flexibility and Robustness in Edge EnvironmentsInternational Journal of Networking and Computing10.15803/ijnc.14.2_12314:2(123-144)Online publication date: 2024
https://doi.org/10.15803/ijnc.14.2_123
Marchesin SSilvello G(2024)Efficient and Reliable Estimation of Knowledge Graph AccuracyProceedings of the VLDB Endowment10.14778/3665844.366586517:9(2392-2403)Online publication date: 1-May-2024
https://dl.acm.org/doi/10.14778/3665844.3665865
Rippon MFleming LChen TRogers AOusey K(2024)Artificial intelligence in wound care: diagnosis, assessment and treatment of hard-to-heal wounds: a narrative reviewJournal of Wound Care10.12968/jowc.2024.33.4.22933:4(229-242)Online publication date: 2-Apr-2024
https://doi.org/10.12968/jowc.2024.33.4.229
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Digital Edition

View this article in digital edition.

Digital Edition

Magazine Site

View this article on the magazine site (external)

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Article

Media

Figures

Other

Tables

View Issue’s Table of Contents