{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T01:06:15Z","timestamp":1775178375636,"version":"3.50.1"},"reference-count":43,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2018,4,24]],"date-time":"2018-04-24T00:00:00Z","timestamp":1524528000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1065251"],"award-info":[{"award-number":["IIS-1065251"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["FA8750-13-2-0005"],"award-info":[{"award-number":["FA8750-13-2-0005"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-17-1-0218"],"award-info":[{"award-number":["FA9550-17-1-0218"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Commun. ACM"],"published-print":{"date-parts":[[2018,4,24]]},"abstract":"<jats:p>\n            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\n            <jats:italic>never-ending learning<\/jats:italic>\n            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.,\n            <jats:italic>servedWith(tea,biscuits)<\/jats:italic>\n            ), 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.\n          <\/jats:p>","DOI":"10.1145\/3191513","type":"journal-article","created":{"date-parts":[[2018,4,25]],"date-time":"2018-04-25T12:22:17Z","timestamp":1524658937000},"page":"103-115","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":397,"title":["Never-ending learning"],"prefix":"10.1145","volume":"61","author":[{"given":"T.","family":"Mitchell","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"W.","family":"Cohen","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"E.","family":"Hruschka","sequence":"additional","affiliation":[{"name":"Federal University of S\u00e3o Carlos, Brazil"}]},{"given":"P.","family":"Talukdar","sequence":"additional","affiliation":[{"name":"Indian Institute of Science, India"}]},{"given":"B.","family":"Yang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"J.","family":"Betteridge","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"A.","family":"Carlson","sequence":"additional","affiliation":[{"name":"Google Inc."}]},{"given":"B.","family":"Dalvi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"M.","family":"Gardner","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"B.","family":"Kisiel","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"J.","family":"Krishnamurthy","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"N.","family":"Lao","sequence":"additional","affiliation":[{"name":"Google Inc."}]},{"given":"K.","family":"Mazaitis","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"T.","family":"Mohamed","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"N.","family":"Nakashole","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"E.","family":"Platanios","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"A.","family":"Ritter","sequence":"additional","affiliation":[{"name":"Ohio State University"}]},{"given":"M.","family":"Samadi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"B.","family":"Settles","sequence":"additional","affiliation":[{"name":"Duolingo"}]},{"given":"R.","family":"Wang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"D.","family":"Wijaya","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"A.","family":"Gupta","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"X.","family":"Chen","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"A.","family":"Saparov","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"M.","family":"Greaves","sequence":"additional","affiliation":[{"name":"Alpine Data Labs"}]},{"given":"J.","family":"Welling","sequence":"additional","affiliation":[{"name":"Pittsburgh Supercomputing Center"}]}],"member":"320","published-online":{"date-parts":[[2018,4,24]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/11503415_8"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279962"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/3023476.3023483"},{"key":"e_1_2_1_6_1","unstructured":"Callan J. Clueweb12 data set (2013; http:\/\/lemurproject.org\/clueweb12\/.  Callan J. Clueweb12 data set (2013; http:\/\/lemurproject.org\/clueweb12\/."},{"key":"e_1_2_1_7_1","unstructured":"Callan J. Hoy M. Clueweb09 data set (2009) http:\/\/boston.lti.cs.cmu.edu\/Data\/clueweb09\/.  Callan J. Hoy M. Clueweb09 data set (2009) http:\/\/boston.lti.cs.cmu.edu\/Data\/clueweb09\/."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/2898607.2898816"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1718487.1718501"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3086758"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.178"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/295240.295725"},{"key":"e_1_2_1_14_1","series-title":"Series B","volume-title":"Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc","author":"Dempster A.","year":"1977","unstructured":"Dempster , A. , Laird , N. , Rubin , D. Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc . Series B ( 1977 ). Dempster, A., Laird, N., Rubin, D. Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. Series B (1977)."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1458082.1458165"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISDA.2014.7066260"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/988672.988687"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/2283396.2283398"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1044"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002545"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(87)90050-6"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122365"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/2145432.2145494"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(83)80005-8"},{"key":"e_1_2_1_25_1","first-page":"2579","volume":"9","author":"Maaten L.v.d.","unstructured":"Maaten , L.v.d. , Hinton , G. Visualizing data using t- SNE. J. Machine Learning Res. 9 , Nov (2008): 2579 -- 2605 . Maaten, L.v.d., Hinton, G. Visualizing data using t-SNE. J. Machine Learning Res. 9, Nov (2008):2579--2605.","journal-title":"SNE. J. Machine Learning Res."},{"key":"e_1_2_1_26_1","volume-title":"J.C. THEO: A framework for self-improving systems. Arch. for Intel.","author":"Mitchell T.M.","year":"1991","unstructured":"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. 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."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/2886521.2886641"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/2145432.2145586"},{"key":"e_1_2_1_29_1","volume-title":"Machine invention of first-order predicates by inverting resolution. Inductivelogic programming","author":"Muggleton S.","year":"1992","unstructured":"Muggleton , S. , Buntine , W. Machine invention of first-order predicates by inverting resolution. Inductivelogic programming ( 1992 ), 261--280. Muggleton, S., Buntine, W. Machine invention of first-order predicates by inverting resolution. Inductivelogic programming (1992), 261--280."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007692713085"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34654-5_24"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/3020751.3020822"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045540"},{"key":"e_1_2_1_34_1","volume-title":"Estimating Accuracy from Unlabeled Data: A Probabilistic Logic Approach","author":"Platanios E.A.","year":"2017","unstructured":"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. 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."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-41335-3_34"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.5555\/2891460.2891622"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242667"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/0921-8890(95)00004-Y"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/296635"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/1642194.1642209"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2007.104"},{"key":"e_1_2_1_42_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Wieting J.","year":"2015","unstructured":"Wieting , J. , Bansal , M. , Gimpel , K. , Livescu , K. Towards universal paraphrastic sentence embeddings . In Proceedings of the International Conference on Learning Representations (ICLR) ( 2015 ). Wieting, J., Bansal, M., Gimpel, K., Livescu, K. Towards universal paraphrastic sentence embeddings. In Proceedings of the International Conference on Learning Representations (ICLR) (2015)."},{"key":"e_1_2_1_44_1","volume-title":"Leveraging knowledge bases in lstms for improving machine reading. ACL","author":"Yang B.","year":"2017","unstructured":"Yang , B. , Mitchell , T. Leveraging knowledge bases in lstms for improving machine reading. ACL ( 2017 ). Yang, B., Mitchell, T. Leveraging knowledge bases in lstms for improving machine reading. ACL (2017)."}],"container-title":["Communications of the ACM"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3191513","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3191513","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3191513","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:11:31Z","timestamp":1750212691000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3191513"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4,24]]},"references-count":43,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2018,4,24]]}},"alternative-id":["10.1145\/3191513"],"URL":"https:\/\/doi.org\/10.1145\/3191513","relation":{},"ISSN":["0001-0782","1557-7317"],"issn-type":[{"value":"0001-0782","type":"print"},{"value":"1557-7317","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,4,24]]},"assertion":[{"value":"2018-04-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}