Never-Ending Learning

T. Mitchell; W. Cohen; E. Hruschka; P. Talukdar; J. Betteridge; A. Carlson; B. Dalvi; M. Gardner; B. Kisiel.; J. Krishnamurthy; N. Lao; K. Mazaitis; T. Mohamed; N. Nakashole; E. Platanios; A. Ritter; M. Samadi; B. Settles; R. Wang; D. Wijaya; A. Gupta; X. Chen; A. Saparov; M. Greaves; J. Welling

Never-Ending Learning

T. Mitchell, W. Cohen, E. Hruschka, P. Talukdar, J. Betteridge, A. Carlson, B. Dalvi, M. Gardner, B. Kisiel., J. Krishnamurthy, N. Lao, K. Mazaitis, T. Mohamed, N. Nakashole, E. Platanios, A. Ritter, M. Samadi, B. Settles, R. Wang, D. WijayaA. Gupta, X. Chen, A. Saparov, M. Greaves, J. Welling

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Other › peer-review

209 Citations (Scopus)

Abstract

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 for machine learning, to better reflect the more ambitious and encompassing type of learning performed by humans. As a case study, we describe the Never-Ending Language Learner (NELL), which achieves some of the desired properties of a never-ending learner, and we discuss lessons learned. NELL has been learning to read the web 24 hours/day since January 2010, and so far has acquired a knowledge base with over 80 million confidence-weighted beliefs (e.g., servedWith(tea, biscuits)), while learning continually to improve its reading competence over time. NELL has also learned to reason over its knowledge base to infer new beliefs from old ones, and is now beginning to extend its ontology by synthesizing new relational predicates. NELL can be tracked online at http://rtw.ml.cmu.edu, and followed on Twitter at @CMUNELL.

Original language	English
Title of host publication	Proceedings of the 29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015
Publisher	Association for the Advancement of Artificial Intelligence (AAAI)
Pages	2302-2310
Number of pages	9
ISBN (Electronic)	9781577357018
Publication status	Published - 1 Jun 2015
Externally published	Yes
Event	AAAI Conference on Artificial Intelligence 2015 - Hyatt Regency, Austin, United States of America Duration: 25 Jan 2015 → 30 Jan 2015 Conference number: 29th http://www.aaai.org/Conferences/AAAI/aaai15.php

Publication series

Name	Proceedings of the National Conference on Artificial Intelligence
Volume	3

Conference

Conference	AAAI Conference on Artificial Intelligence 2015
Abbreviated title	AAAI 2015
Country/Territory	United States of America
City	Austin
Period	25/01/15 → 30/01/15
Other	co-located with the 27th Innovative Applications of Artificial Intelligence Conference
Internet address	http://www.aaai.org/Conferences/AAAI/aaai15.php

Cite this

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., ... Welling, J. (2015). Never-Ending Learning. In Proceedings of the 29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015 (pp. 2302-2310). (Proceedings of the National Conference on Artificial Intelligence; Vol. 3). Association for the Advancement of Artificial Intelligence (AAAI).

Mitchell, T. ; Cohen, W. ; Hruschka, E. et al. / Never-Ending Learning. Proceedings of the 29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015. Association for the Advancement of Artificial Intelligence (AAAI), 2015. pp. 2302-2310 (Proceedings of the National Conference on Artificial Intelligence).

@inproceedings{a1d29ce355f74d129477fb0d6df00a78,

title = "Never-Ending Learning",

abstract = "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 for machine learning, to better reflect the more ambitious and encompassing type of learning performed by humans. As a case study, we describe the Never-Ending Language Learner (NELL), which achieves some of the desired properties of a never-ending learner, and we discuss lessons learned. NELL has been learning to read the web 24 hours/day since January 2010, and so far has acquired a knowledge base with over 80 million confidence-weighted beliefs (e.g., servedWith(tea, biscuits)), while learning continually to improve its reading competence over time. NELL has also learned to reason over its knowledge base to infer new beliefs from old ones, and is now beginning to extend its ontology by synthesizing new relational predicates. NELL can be tracked online at http://rtw.ml.cmu.edu, and followed on Twitter at @CMUNELL.",

author = "T. Mitchell and W. Cohen and E. Hruschka and P. Talukdar and J. Betteridge and A. Carlson and B. Dalvi and M. Gardner and B. Kisiel. and J. Krishnamurthy and N. Lao and K. Mazaitis and T. Mohamed and N. Nakashole and E. Platanios and A. Ritter and M. Samadi and B. Settles and R. Wang and D. Wijaya and A. Gupta and X. Chen and A. Saparov and M. Greaves and J. Welling",

note = "Publisher Copyright: {\textcopyright} Copyright 2015, Association for the Advancement of Artificial Intelligence (www.aaa1.org). All rights reserved.; AAAI Conference on Artificial Intelligence 2015, AAAI 2015 ; Conference date: 25-01-2015 Through 30-01-2015",

year = "2015",

month = jun,

day = "1",

language = "English",

series = "Proceedings of the National Conference on Artificial Intelligence",

publisher = "Association for the Advancement of Artificial Intelligence (AAAI)",

pages = "2302--2310",

booktitle = "Proceedings of the 29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015",

address = "United States of America",

url = "http://www.aaai.org/Conferences/AAAI/aaai15.php",

}

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 2015, Never-Ending Learning. in Proceedings of the 29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015. Proceedings of the National Conference on Artificial Intelligence, vol. 3, Association for the Advancement of Artificial Intelligence (AAAI), pp. 2302-2310, AAAI Conference on Artificial Intelligence 2015, Austin, Texas, United States of America, 25/01/15.

Never-Ending Learning. / Mitchell, T.; Cohen, W.; Hruschka, E. et al.
Proceedings of the 29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015. Association for the Advancement of Artificial Intelligence (AAAI), 2015. p. 2302-2310 (Proceedings of the National Conference on Artificial Intelligence; Vol. 3).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Other › peer-review

TY - GEN

T1 - Never-Ending Learning

AU - Mitchell, T.

AU - Cohen, W.

AU - Hruschka, E.

AU - Talukdar, P.

AU - Betteridge, J.

AU - Carlson, A.

AU - Dalvi, B.

AU - Gardner, M.

AU - Kisiel., B.

AU - Krishnamurthy, J.

AU - Lao, N.

AU - Mazaitis, K.

AU - Mohamed, T.

AU - Nakashole, N.

AU - Platanios, E.

AU - Ritter, A.

AU - Samadi, M.

AU - Settles, B.

AU - Wang, R.

AU - Wijaya, D.

AU - Gupta, A.

AU - Chen, X.

AU - Saparov, A.

AU - Greaves, M.

AU - Welling, J.

N1 - Conference code: 29th

PY - 2015/6/1

Y1 - 2015/6/1

N2 - 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 for machine learning, to better reflect the more ambitious and encompassing type of learning performed by humans. As a case study, we describe the Never-Ending Language Learner (NELL), which achieves some of the desired properties of a never-ending learner, and we discuss lessons learned. NELL has been learning to read the web 24 hours/day since January 2010, and so far has acquired a knowledge base with over 80 million confidence-weighted beliefs (e.g., servedWith(tea, biscuits)), while learning continually to improve its reading competence over time. NELL has also learned to reason over its knowledge base to infer new beliefs from old ones, and is now beginning to extend its ontology by synthesizing new relational predicates. NELL can be tracked online at http://rtw.ml.cmu.edu, and followed on Twitter at @CMUNELL.

AB - 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 for machine learning, to better reflect the more ambitious and encompassing type of learning performed by humans. As a case study, we describe the Never-Ending Language Learner (NELL), which achieves some of the desired properties of a never-ending learner, and we discuss lessons learned. NELL has been learning to read the web 24 hours/day since January 2010, and so far has acquired a knowledge base with over 80 million confidence-weighted beliefs (e.g., servedWith(tea, biscuits)), while learning continually to improve its reading competence over time. NELL has also learned to reason over its knowledge base to infer new beliefs from old ones, and is now beginning to extend its ontology by synthesizing new relational predicates. NELL can be tracked online at http://rtw.ml.cmu.edu, and followed on Twitter at @CMUNELL.

UR - http://www.scopus.com/inward/record.url?scp=84954123466&partnerID=8YFLogxK

M3 - Conference Paper

AN - SCOPUS:84954123466

T3 - Proceedings of the National Conference on Artificial Intelligence

SP - 2302

EP - 2310

BT - Proceedings of the 29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015

PB - Association for the Advancement of Artificial Intelligence (AAAI)

T2 - AAAI Conference on Artificial Intelligence 2015

Y2 - 25 January 2015 through 30 January 2015

ER -

Mitchell T, Cohen W, Hruschka E, Talukdar P, Betteridge J, Carlson A et al. Never-Ending Learning. In Proceedings of the 29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015. Association for the Advancement of Artificial Intelligence (AAAI). 2015. p. 2302-2310. (Proceedings of the National Conference on Artificial Intelligence).

Never-Ending Learning

Abstract

Publication series

Conference

Other files and links

Never-ending learning

Cite this