TY - JOUR AU - Mitchell, Tom AU - Cohen, William AU - Hruschka, Estevam AU - Talukdar, Partha AU - Betteridge, Justin AU - Carlson, Andrew AU - Dalvi Mishra, Bhavana AU - Gardner, Matthew AU - Kisiel, Bryan AU - Krishnamurthy, Jayant AU - Lao, Ni AU - Mazaitis, Kathryn AU - Mohamed, Thahir AU - Nakashole, Ndapa AU - Platanios, Emmanouil AU - Ritter, Alan AU - Samadi, Mehdi AU - Settles, Burr AU - Wang, Richard AU - Wijaya, Derry AU - Gupta, Abhinav AU - Chen, Xinlei AU - Saparov, Abulhair AU - Greaves, Malcolm AU - Welling, Joel PY - 2015/02/19 Y2 - 2024/03/19 TI - Never-Ending Learning JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 29 IS - 1 SE - Main Track: NLP and Machine Learning DO - 10.1609/aaai.v29i1.9498 UR - https://ojs.aaai.org/index.php/AAAI/article/view/9498 SP - AB - <p> 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., <em>servedWith(tea, biscuits)</em>). NELL has also learned millions of features and parameters that enable it to read these beliefs from the web. Additionally, it has learned to reason over these beliefs to infer new beliefs, and is able 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. </p> ER -