143:
commonsense knowledge. For instance, when a machine is used to translate a text, problems of ambiguity arise, which could be easily resolved by attaining a concrete and true understanding of the context. Online translators often resolve ambiguities using analogous or similar words. For example, in translating the sentences "The electrician is working" and "The telephone is working" into German, the machine translates correctly "working" in the means of "laboring" in the first one and as "functioning properly" in the second one. The machine has seen and read in the body of texts that the German words for "laboring" and "electrician" are frequently used in a combination and are found close together. The same applies for "telephone" and "function properly". However, the statistical proxy which works in simple cases often fails in complex ones. Existing computer programs carry out simple language tasks by manipulating short phrases or separate words, but they don't attempt any deeper understanding and focus on short-term results.
152:
In an isolated image they would be difficult to identify. Movies prove to be even more difficult tasks. Some movies contain scenes and moments that cannot be understood by simply matching memorized templates to images. For instance, to understand the context of the movie, the viewer is required to make inferences about characters’ intentions and make presumptions depending on their behavior. In the contemporary state of the art, it is impossible to build and manage a program that will perform such tasks as reasoning, i.e. predicting characters’ actions. The most that can be done is to identify basic actions and track characters.
104:" that helps them to interpret natural-language sentences such as "The city councilmen refused the demonstrators a permit because they advocated violence". (A generic AI has difficulty discerning whether the ones alleged to be advocating violence are the councilmen or the demonstrators.) This lack of "common knowledge" means that AI often makes different mistakes than humans make, in ways that can seem incomprehensible. For example, existing self-driving cars cannot reason about the location nor the intentions of pedestrians in the exact way that humans do, and instead must use non-human modes of reasoning to avoid accidents.
88:
412:
approaches. The mathematically grounded approaches are purely theoretical and the result is a printed paper instead of a program. The work is limited to the range of the domains and the reasoning techniques that are being reflected on. In informal knowledge-based approaches, theories of reasoning are based on anecdotal data and intuition that are results from empirical behavioral psychology. Informal approaches are common in computer programming. Two other popular techniques for extracting commonsense knowledge from Web documents involve
434:, claims to generate commonsense inferences at a level approaching human benchmarks. Like many other current efforts, COMET over-relies on surface language patterns and is judged to lack deep human-level understanding of many commonsense concepts. Other language-model approaches include training on visual scenes rather than just text, and training on textual descriptions of scenarios involving commonsense physics.
335:
wolves and lambs and the number of wolves decreases, the death rate of the lambs will go down as well. This theory was firstly formulated by Johan de Kleer, who analyzed an object moving on a roller coaster. The theory of qualitative reasoning is applied in many spheres such as physics, biology, engineering, ecology, etc. It serves as the basis for many practical programs, analogical mapping, text understanding.
407:
Commonsense's reasoning study is divided into knowledge-based approaches and approaches that are based on machine learning over and using a large data corpora with limited interactions between these two types of approaches . There are also crowdsourcing approaches, attempting to construct a knowledge
358:
Second, situations that seem easily predicted or assumed about could have logical complexity, which humans’ commonsense knowledge does not cover. Some aspects of similar situations are studied and are well understood, but there are many relations that are unknown, even in principle and how they could
321:
Temporal reasoning is the ability to make presumptions about humans' knowledge of times, durations and time intervals. For example, if an individual knows that Mozart was born after Haydn and died earlier than him, they can use their temporal reasoning knowledge to deduce that Mozart had died younger
78:
NYU professor Ernest Davis characterizes commonsense knowledge as "what a typical seven year old knows about the world", including physical objects, substances, plants, animals, and human society. It usually excludes book-learning, specialized knowledge, and knowledge of conventions; but it sometimes
411:
In knowledge-based approaches, the experts are analyzing the characteristics of the inferences that are required to do reasoning in a specific area or for a certain task. The knowledge-based approaches consist of mathematically grounded approaches, informal knowledge-based approaches and large-scale
343:
As of 2014, there are some commercial systems trying to make the use of commonsense reasoning significant. However, they use statistical information as a proxy for commonsense knowledge, where reasoning is absent. Current programs manipulate individual words, but they don't attempt or offer further
151:
Issues of this kind arise in computer vision. For instance when looking at a photograph of a bathroom some items that are small and only partly seen, such as facecloths and bottles, are recognizable due to the surrounding objects (toilet, wash basin, bathtub), which suggest the purpose of the room.
121:
The commonsense knowledge problem is a current project in the sphere of artificial intelligence to create a database that contains the general knowledge most individuals are expected to have, represented in an accessible way to artificial intelligence programs that use natural language. Due to the
334:
Qualitative reasoning is the form of commonsense reasoning analyzed with certain success. It is concerned with the direction of change in interrelated quantities. For instance, if the price of a stock goes up, the amount of stocks that are going to be sold will go down. If some ecosystem contains
164:
that work in a real-life uncontrolled environment is evident. For instance, if a robot is programmed to perform the tasks of a waiter at a cocktail party, and it sees that the glass he had picked up is broken, the waiter-robot should not pour the liquid into the glass, but instead pick up another
38:
is a human-like ability to make presumptions about the type and essence of ordinary situations humans encounter every day. These assumptions include judgments about the nature of physical objects, taxonomic properties, and peoples' intentions. A device that exhibits commonsense reasoning might be
142:
first discussed the need and significance of practical knowledge for natural language processing in the context of machine translation. Some ambiguities are resolved by using simple and easy to acquire rules. Others require a broad acknowledgement of the surrounding world, thus they require more
122:
broad scope of the commonsense knowledge, this issue is considered to be among the most difficult problems in AI research. In order for any task to be done as a human mind would manage it, the machine is required to appear as intelligent as a human being. Such tasks include
364:
Third, commonsense reasoning involves plausible reasoning. It requires coming to a reasonable conclusion given what is already known. Plausible reasoning has been studied for many years and there are a lot of theories developed that include probabilistic reasoning and
173:
Significant progress in the field of the automated commonsense reasoning is made in the areas of the taxonomic reasoning, actions and change reasoning, reasoning about time. Each of these spheres has a well-acknowledged theory for wide range of commonsense inferences.
293:
Events are atomic, meaning one event occurs at a time and the reasoner needs to consider the state and condition of the world at the start and at the finale of the specific event, but not during the states, while there is still an evidence of on-going changes
59:"Commonsense knowledge includes the basic facts about events (including actions) and their effects, facts about knowledge and how it is obtained, facts about beliefs and desires. It also includes the basic facts about material objects and their properties."
91:
A self-driving car system may use a neural network to determine which parts of the picture seem to match previous training images of pedestrians, and then model those areas as slow-moving but somewhat unpredictable rectangular prisms that must be
352:
First, some of the domains that are involved in commonsense reasoning are only partly understood. Individuals are far from a comprehensive understanding of domains such as communication and knowledge, interpersonal interactions or physical
280:
is a resource including a taxonomy, whose elements are meanings of
English words. Web mining systems used to collect commonsense knowledge from Web documents focus on taxonomic relations and specifically in gathering taxonomic relations.
100:" such as space, time, and physical interactions. This enables even young children to easily make inferences like "If I roll this pen off a table, it will fall on the floor". Humans also have a powerful mechanism of "
79:
includes knowledge about those topics. For example, knowing how to play cards is specialized knowledge, not "commonsense knowledge"; but knowing that people play cards for fun does count as "commonsense knowledge".
276:. When an individual taxonomizes more abstract categories, outlining and delimiting specific categories becomes more problematic. Simple taxonomic structures are frequently used in AI programs. For instance,
326:, is more challenging, because natural language expressions have context dependent interpretation. Simple tasks such as assigning timestamps to procedures cannot be done with total accuracy.
1306:
289:
The theory of action, events and change is another range of the commonsense reasoning. There are established reasoning methods for domains that satisfy the constraints listed below:
720:
1160:
Hageback, Niklas. (2017). The
Virtual Mind: Designing the Logic to Approximate Human Thinking (Chapman & Hall/CRC Artificial Intelligence and Robotics Series) 1st Edition.
689:
408:
basis by linking the collective knowledge and the input of non-expert people. Knowledge-based approaches can be separated into approaches based on mathematical logic .
399:
data is insufficient to produce an artificial general intelligence capable of commonsense reasoning, and have therefore turned to less-supervised learning techniques.
107:
Overlapping subtopics of commonsense reasoning include quantities and measurements, time and space, physics, minds, society, plans and goals, and actions and change.
322:
than Haydn. The inferences involved reduce themselves to solving systems of linear inequalities. To integrate that kind of reasoning with concrete purposes, such as
526:
Matuszek, Cynthia, et al. "Searching for common sense: Populating cyc from the web." UMBC Computer
Science and Electrical Engineering Department Collection (2005).
490:
McCarthy, John. "Artificial intelligence, logic and formalizing common sense." Philosophical logic and artificial intelligence. Springer, Dordrecht, 1989. 161-190.
465:
300:
Events are deterministic, meaning the world's state at the end of the event is defined by the world's state at the beginning and the specification of the event.
982:
165:
one. Such tasks seem obvious when an individual possesses simple commonsense reasoning, but to ensure that a robot will avoid such mistakes is challenging.
96:
Compared with humans, existing AI lacks several features of human commonsense reasoning; most notably, humans have powerful mechanisms for reasoning about "
374:
Fourth, there are many domains, in which a small number of examples are extremely frequent, whereas there is a vast number of highly infrequent examples.
1211:
383:
Compared with humans, as of 2018 existing computer programs perform extremely poorly on modern "commonsense reasoning" benchmark tests such as the
859:
624:
116:
62:"Commonsense knowledge differs from encyclopedic knowledge in that it deals with general knowledge rather than the details of specific entities."
1020:
Bosselut, Antoine, et al. "Comet: Commonsense transformers for automatic knowledge graph construction." arXiv preprint arXiv:1906.05317 (2019).
65:
Commonsense knowledge is "real world knowledge that can provide a basis for additional knowledge to be gathered and interpreted automatically".
1313:
74:
Common sense is "broadly reusable background knowledge that's not specific to a particular subject area... knowledge that you ought to have."
924:." International Conference on Knowledge-Based and Intelligent Information and Engineering Systems. Springer, Berlin, Heidelberg, 2004.
130:. To perform them, the machine has to be aware of the same concepts that an individual, who possess commonsense knowledge, recognizes.
934:
917:
996:
1322:
17:
712:
681:
1157:| Encyclopedia.com: FREE online dictionary. Available at: http://www.encyclopedia.com/doc/1O88-commonsenseknowledge.html .
1165:
1137:
1052:
500:
Tandon, Niket; Varde, Aparna S.; de Melo, Gerard (22 February 2018). "Commonsense
Knowledge in Machine Intelligence".
1590:
1118:
1092:
1068:
1042:
369:. It takes different forms that include using unreliable data and rules, whose conclusions are not certain sometimes.
536:
392:
387:. The problem of attaining human-level competency at "commonsense knowledge" tasks is considered to probably be "
1580:
323:
316:
1415:
1649:
1570:
1486:
1400:
1299:
566:
1466:
1443:
1395:
1247:
825:
379:
Fifth, when formulating presumptions it is challenging to discern and determine the level of abstraction.
182:
Taxonomy is the collection of individuals and categories and their relations. Three basic relations are:
1219:
632:
71:
Common sense is "all the knowledge about the world that we take for granted but rarely state out loud".
972:
Yampolskiy, Roman V. "AI-Complete, AI-Hard, or AI-Easy-Classification of
Problems in AI." MAICS. 2012.
1613:
1423:
384:
1109:
The
Emotion Machine: Commonsense Thinking, Artificial Intelligence, and the Future of the Human Mind
797:
1527:
948:
839:
713:"Boston may be famous for bad drivers, but it's the testing ground for a smarter self-driving car"
1557:
872:
31:
1186:
776:
1608:
1565:
1542:
1522:
1428:
1187:
CYC: Using Common Sense
Knowledge to Overcome Brittleness and Knowledge Acquisition Bottlenecks
1082:
348:, five major obstacles interfere with the producing of a satisfactory "commonsense reasoner".
1491:
1372:
1357:
784:
811:
1623:
1603:
1433:
1342:
1150:. Available at: https://www.edx.org/course/artificial-intelligence-uc-berkeleyx-cs188-1x .
914:
68:
The commonsense world consists of "time, space, physical interactions, people, and so on".
8:
1405:
1326:
1291:
886:
396:
366:
139:
87:
1644:
1512:
1286:
1031:
123:
55:
Some definitions and characterizations of common sense from different authors include:
1207:. Available at: http://psych.utoronto.ca/users/reingold/courses/ai/commonsense.html .
1175:. Elsevier. Available at: http://www.journals.elsevier.com/artificial-intelligence/ .
306:
The relevant state of the world at the beginning is either known or can be calculated.
1618:
1575:
1547:
1458:
1438:
1337:
1161:
1133:
1114:
1107:
1088:
1064:
1057:
1038:
667:
900:
1362:
1352:
1271:
755:
663:
604:
509:
473:
161:
1239:. Available at: https://www.theguardian.com/technology/artificialintelligenceai .
97:
1598:
1367:
1197:
921:
844:
101:
40:
27:
Branch of artificial intelligence aiming to create AI systems with "common sense"
1281:
417:
760:
743:
43:(humans' innate ability to reason about people's behavior and intentions) and
1638:
1382:
1102:
1078:
862:." Proceedings of the IEEE international conference on computer vision. 2015.
430:
language model architecture and existing commonsense knowledge bases such as
44:
513:
466:"Commonsense Reasoning and Commonsense Knowledge in Artificial Intelligence"
1448:
388:
345:
127:
186:
An individual is an instance of a category. For example, the individual
1287:
Knowledge
Infusion: In Pursuit of Robustness in Artificial Intelligence
431:
413:
1248:
https://www.udacity.com/course/intro-to-artificial-intelligence--cs271
609:
592:
744:"On the problem of making autonomous vehicles conform to traffic law"
682:"Don't worry: Autonomous cars aren't coming tomorrow (or next year)"
477:
1266:
654:
Winograd, Terry (January 1972). "Understanding natural language".
1532:
1476:
997:"Computers Already Learn From Us. But Can They Teach Themselves?"
840:"Bar Hillel Artificial Intelligence Research Machine Translation"
391:" (that is, solving it would require the ability to synthesize a
338:
277:
1507:
424:
168:
1537:
1517:
1481:
1390:
1182:. Available at: http://www.leaderu.com/truth/2truth07.html .
427:
1205:
Artificial
Intelligence | The Common Sense Knowledge Problem
1471:
1276:
1244:
Intro to
Artificial Intelligence Course and Training Online
593:"Logical Formalizations of Commonsense Reasoning: A Survey"
39:
capable of drawing conclusions that are similar to humans'
1321:
1256:. Available at: http://www.w3.org/People/Raggett/Sense/ .
1132:(2nd ed.). Waltham, Mass.: Morgan Kaufmann/Elsevier.
303:
There is a single actor and all events are their actions.
220:
Transitivity is one type of inference in taxonomy. Since
1237:
Artificial intelligence (AI) | Technology | The Guardian
1198:
Common Sense, the Turing Test, and the Quest for Real AI
537:"How to Teach Artificial Intelligence Some Common Sense"
1130:
Commonsense Reasoning: An Event Calculus Based Approach
463:
47:(humans' natural understanding of the physical world).
359:
be represented in a form that is usable by computers.
160:
The need and importance of commonsense reasoning in
50:
1153:Encyclopedia.com, (2015). "commonsense knowledge."
133:
1106:
1056:
1030:
915:Commonsense reasoning in and over natural language
499:
244:. Inheritance is another type of inference. Since
197:One category is a subset of another. For instance
1282:The Epilog project at the University of Rochester
1180:ARTIFICIAL INTELLIGENCE AS COMMON SENSE KNOWLEDGE
625:"Cultivating Common Sense | DiscoverMagazine.com"
1636:
1185:Lenat, D., Prakash, M. and Shepherd, M. (1985).
110:
82:
981:Andrich, C, Novosel, L, and Hrnkas, B. (2009).
117:Commonsense knowledge (artificial intelligence)
459:
457:
455:
453:
451:
449:
447:
339:Challenges in automating commonsense reasoning
1307:
1212:"CommonSense - Knowledge Management Overview"
472:. Vol. 58, no. 9. pp. 92–103.
344:understanding. According to Ernest Davis and
297:Every single change is a result of some event
887:"Action and change in Commonsense reasoning"
402:
169:Successes in automated commonsense reasoning
597:Journal of Artificial Intelligence Research
444:
1314:
1300:
1277:Media Lab Commonsense Computing Initiative
208:Two categories are disjoint. For instance
985:. Information Search and Retrieval, 2009.
759:
608:
1051:
1033:Representations of Commonsense Reasoning
774:
653:
560:
558:
329:
86:
1127:
741:
155:
14:
1637:
1101:
1077:
1037:. San Mateo, Calif.: Morgan Kaufmann.
826:"Artificial intelligence applications"
710:
564:
177:
1295:
1028:
994:
590:
555:
310:
284:
777:"Logic and Artificial Intelligence"
723:from the original on 22 August 2020
24:
1272:Commonsense Reasoning Problem Page
812:"Artificial intelligence Programs"
692:from the original on 25 March 2018
464:Ernest Davis; Gary Marcus (2015).
423:COMET (2019), which uses both the
146:
25:
1661:
1260:
775:Thomason, Richmond (2003-08-27).
742:Prakken, Henry (31 August 2017).
567:"Common Sense Comes to Computers"
395:). Some researchers believe that
51:Definitions and characterizations
1113:. New York: Simon and Schuster.
1087:. New York: Simon and Schuster.
995:Smith, Craig S. (8 April 2020).
591:Davis, Ernest (25 August 2017).
134:Commonsense in intelligent tasks
1014:
988:
975:
966:
949:"The Winograd Schema Challenge"
941:
927:
907:
893:
879:
865:
852:
832:
818:
804:
768:
748:Artificial Intelligence and Law
735:
704:
674:
324:natural language interpretation
190:is an instance of the category
1267:Commonsense Reasoning Web Site
860:Vqa: Visual question answering
647:
617:
584:
565:Pavlus, John (30 April 2020).
529:
520:
493:
484:
13:
1:
437:
111:Commonsense knowledge problem
83:Commonsense reasoning problem
1571:Constraint logic programming
1487:Knowledge Interchange Format
1444:Procedural reasoning systems
1401:Expert systems for mortgages
1396:Connectionist expert systems
913:Liu, Hugo, and Push Singh. "
668:10.1016/0010-0285(72)90002-3
7:
1467:Attempto Controlled English
1254:Computers with Common Sense
1203:Psych.utoronto.ca, (2015).
10:
1666:
858:Antol, Stanislaw, et al. "
317:Spatial–temporal reasoning
314:
126:, machine translation and
114:
1614:Preference-based planning
1589:
1556:
1500:
1457:
1414:
1381:
1333:
1171:Intelligence, A. (2015).
1155:A Dictionary of Sociology
1128:Mueller, Erik T. (2015).
761:10.1007/s10506-017-9210-0
470:Communications of the ACM
403:Approaches and techniques
385:Winograd Schema Challenge
1323:Knowledge representation
1063:. Norwood, N.J.: Ablex.
1059:Formalizing Common Sense
393:human-level intelligence
260:is marked with property
1558:Constraint satisfaction
1173:Artificial Intelligence
1148:Artificial Intelligence
935:"Qualitative reasoning"
514:10.1145/3186549.3186562
252:, which is a subset of
32:artificial intelligence
1609:Partial-order planning
1566:Constraint programming
1235:the Guardian, (2015).
1218:. 2015. Archived from
1029:Davis, Ernest (1990).
983:Common Sense Knowledge
792:Cite journal requires
631:. 2017. Archived from
93:
18:Common sense reasoning
1492:Web Ontology Language
1434:Deductive classifiers
1373:Knowledge engineering
1358:Model-based reasoning
1348:Commonsense reasoning
1242:Udacity.com, (2015).
1196:Levesque, H. (2017).
1178:Leaderu.com, (2015).
717:MIT Technology Review
711:Knight, Will (2017).
330:Qualitative reasoning
315:Further information:
90:
36:commonsense reasoning
1624:State space planning
1604:Multi-agent planning
1406:Legal expert systems
1343:Case-based reasoning
901:"Temporal reasoning"
656:Cognitive Psychology
156:Robotic manipulation
1650:Automated reasoning
1193:, 6(4), p. 65.
1084:The Society of Mind
397:supervised learning
367:non-monotonic logic
178:Taxonomic reasoning
1591:Automated planning
1459:Ontology languages
1429:Constraint solvers
1001:The New York Times
920:2017-08-09 at the
543:. 13 November 2018
311:Temporal reasoning
264:, it follows that
248:is an instance of
240:is an instance of
236:, it follows that
224:is an instance of
124:object recognition
94:
1632:
1631:
1619:Reactive planning
1576:Local consistency
1416:Reasoning systems
1363:Inference engines
1338:Backward chaining
1246:. Available at:
1216:Sensesoftware.com
629:Discover Magazine
610:10.1613/jair.5339
502:ACM SIGMOD Record
285:Action and change
212:is disjoint from
162:autonomous robots
16:(Redirected from
1657:
1368:Proof assistants
1353:Forward chaining
1316:
1309:
1302:
1293:
1292:
1252:W3.org, (2015).
1231:
1229:
1227:
1143:
1124:
1112:
1098:
1074:
1062:
1048:
1036:
1021:
1018:
1012:
1011:
1009:
1007:
992:
986:
979:
973:
970:
964:
963:
961:
959:
945:
939:
938:
931:
925:
911:
905:
904:
897:
891:
890:
883:
877:
876:
869:
863:
856:
850:
849:
836:
830:
829:
822:
816:
815:
808:
802:
801:
795:
790:
788:
780:
772:
766:
765:
763:
739:
733:
732:
730:
728:
708:
702:
701:
699:
697:
678:
672:
671:
651:
645:
644:
642:
640:
635:on 25 March 2018
621:
615:
614:
612:
588:
582:
581:
579:
577:
562:
553:
552:
550:
548:
533:
527:
524:
518:
517:
497:
491:
488:
482:
481:
461:
21:
1665:
1664:
1660:
1659:
1658:
1656:
1655:
1654:
1635:
1634:
1633:
1628:
1599:Motion planning
1585:
1552:
1501:Theorem provers
1496:
1453:
1424:Theorem provers
1410:
1377:
1329:
1320:
1263:
1225:
1223:
1222:on 17 July 2015
1210:
1140:
1121:
1095:
1071:
1045:
1025:
1024:
1019:
1015:
1005:
1003:
993:
989:
980:
976:
971:
967:
957:
955:
947:
946:
942:
933:
932:
928:
922:Wayback Machine
912:
908:
899:
898:
894:
885:
884:
880:
871:
870:
866:
857:
853:
845:TheGuardian.com
838:
837:
833:
824:
823:
819:
810:
809:
805:
793:
791:
782:
781:
773:
769:
740:
736:
726:
724:
709:
705:
695:
693:
680:
679:
675:
652:
648:
638:
636:
623:
622:
618:
589:
585:
575:
573:
571:Quanta Magazine
563:
556:
546:
544:
535:
534:
530:
525:
521:
498:
494:
489:
485:
478:10.1145/2701413
462:
445:
440:
405:
341:
332:
319:
313:
287:
232:is a subset of
201:is a subset of
180:
171:
158:
149:
147:Computer vision
136:
119:
113:
102:folk psychology
85:
53:
41:folk psychology
28:
23:
22:
15:
12:
11:
5:
1663:
1653:
1652:
1647:
1630:
1629:
1627:
1626:
1621:
1616:
1611:
1606:
1601:
1595:
1593:
1587:
1586:
1584:
1583:
1578:
1573:
1568:
1562:
1560:
1554:
1553:
1551:
1550:
1545:
1540:
1535:
1530:
1525:
1520:
1515:
1510:
1504:
1502:
1498:
1497:
1495:
1494:
1489:
1484:
1479:
1474:
1469:
1463:
1461:
1455:
1454:
1452:
1451:
1446:
1441:
1439:Logic programs
1436:
1431:
1426:
1420:
1418:
1412:
1411:
1409:
1408:
1403:
1398:
1393:
1387:
1385:
1383:Expert systems
1379:
1378:
1376:
1375:
1370:
1365:
1360:
1355:
1350:
1345:
1340:
1334:
1331:
1330:
1319:
1318:
1311:
1304:
1296:
1290:
1289:
1284:
1279:
1274:
1269:
1262:
1261:External links
1259:
1258:
1257:
1250:
1240:
1233:
1208:
1201:
1194:
1183:
1176:
1169:
1166:978-1138054035
1158:
1151:
1144:
1139:978-0128014165
1138:
1125:
1119:
1103:Minsky, Marvin
1099:
1093:
1079:Minsky, Marvin
1075:
1069:
1053:McCarthy, John
1049:
1043:
1023:
1022:
1013:
987:
974:
965:
940:
926:
906:
892:
878:
864:
851:
831:
817:
803:
794:|journal=
767:
754:(3): 341–363.
734:
703:
673:
646:
616:
583:
554:
528:
519:
492:
483:
442:
441:
439:
436:
418:Crowd sourcing
404:
401:
381:
380:
376:
375:
371:
370:
361:
360:
355:
354:
340:
337:
331:
328:
312:
309:
308:
307:
304:
301:
298:
295:
286:
283:
272:have property
218:
217:
206:
195:
179:
176:
170:
167:
157:
154:
148:
145:
135:
132:
115:Main article:
112:
109:
84:
81:
76:
75:
72:
69:
66:
63:
60:
52:
49:
26:
9:
6:
4:
3:
2:
1662:
1651:
1648:
1646:
1643:
1642:
1640:
1625:
1622:
1620:
1617:
1615:
1612:
1610:
1607:
1605:
1602:
1600:
1597:
1596:
1594:
1592:
1588:
1582:
1579:
1577:
1574:
1572:
1569:
1567:
1564:
1563:
1561:
1559:
1555:
1549:
1546:
1544:
1541:
1539:
1536:
1534:
1531:
1529:
1526:
1524:
1521:
1519:
1516:
1514:
1511:
1509:
1506:
1505:
1503:
1499:
1493:
1490:
1488:
1485:
1483:
1480:
1478:
1475:
1473:
1470:
1468:
1465:
1464:
1462:
1460:
1456:
1450:
1447:
1445:
1442:
1440:
1437:
1435:
1432:
1430:
1427:
1425:
1422:
1421:
1419:
1417:
1413:
1407:
1404:
1402:
1399:
1397:
1394:
1392:
1389:
1388:
1386:
1384:
1380:
1374:
1371:
1369:
1366:
1364:
1361:
1359:
1356:
1354:
1351:
1349:
1346:
1344:
1341:
1339:
1336:
1335:
1332:
1328:
1324:
1317:
1312:
1310:
1305:
1303:
1298:
1297:
1294:
1288:
1285:
1283:
1280:
1278:
1275:
1273:
1270:
1268:
1265:
1264:
1255:
1251:
1249:
1245:
1241:
1238:
1234:
1221:
1217:
1213:
1209:
1206:
1202:
1199:
1195:
1192:
1188:
1184:
1181:
1177:
1174:
1170:
1167:
1163:
1159:
1156:
1152:
1149:
1146:edX, (2014).
1145:
1141:
1135:
1131:
1126:
1122:
1120:0-7432-7663-9
1116:
1111:
1110:
1104:
1100:
1096:
1094:0-671-60740-5
1090:
1086:
1085:
1080:
1076:
1072:
1070:1-871516-49-8
1066:
1061:
1060:
1054:
1050:
1046:
1044:1-55860-033-7
1040:
1035:
1034:
1027:
1026:
1017:
1002:
998:
991:
984:
978:
969:
954:
950:
944:
936:
930:
923:
919:
916:
910:
902:
896:
888:
882:
874:
868:
861:
855:
847:
846:
841:
835:
827:
821:
813:
807:
799:
786:
778:
771:
762:
757:
753:
749:
745:
738:
722:
718:
714:
707:
691:
687:
683:
677:
669:
665:
661:
657:
650:
634:
630:
626:
620:
611:
606:
602:
598:
594:
587:
572:
568:
561:
559:
542:
538:
532:
523:
515:
511:
507:
503:
496:
487:
479:
475:
471:
467:
460:
458:
456:
454:
452:
450:
448:
443:
435:
433:
429:
426:
421:
419:
415:
409:
400:
398:
394:
390:
386:
378:
377:
373:
372:
368:
363:
362:
357:
356:
351:
350:
349:
347:
336:
327:
325:
318:
305:
302:
299:
296:
292:
291:
290:
282:
279:
275:
271:
267:
263:
259:
255:
251:
247:
243:
239:
235:
231:
227:
223:
215:
211:
207:
204:
200:
196:
193:
189:
185:
184:
183:
175:
166:
163:
153:
144:
141:
131:
129:
125:
118:
108:
105:
103:
99:
98:naĂŻve physics
89:
80:
73:
70:
67:
64:
61:
58:
57:
56:
48:
46:
45:naive physics
42:
37:
33:
19:
1449:Rule engines
1347:
1253:
1243:
1236:
1224:. Retrieved
1220:the original
1215:
1204:
1200:. MIT Press.
1190:
1179:
1172:
1154:
1147:
1129:
1108:
1083:
1058:
1032:
1016:
1004:. Retrieved
1000:
990:
977:
968:
956:. Retrieved
952:
943:
929:
909:
895:
881:
867:
854:
843:
834:
820:
806:
785:cite journal
770:
751:
747:
737:
725:. Retrieved
716:
706:
694:. Retrieved
685:
676:
662:(1): 1–191.
659:
655:
649:
637:. Retrieved
633:the original
628:
619:
600:
596:
586:
574:. Retrieved
570:
545:. Retrieved
540:
531:
522:
508:(4): 49–52.
505:
501:
495:
486:
469:
422:
410:
406:
382:
342:
333:
320:
288:
273:
269:
265:
261:
257:
253:
249:
245:
241:
237:
233:
229:
225:
221:
219:
213:
209:
202:
198:
191:
187:
181:
172:
159:
150:
137:
120:
106:
95:
77:
54:
35:
29:
1581:SMT solvers
1191:AI Magazine
603:: 651–723.
547:11 February
389:AI complete
346:Gary Marcus
294:(progress).
128:text mining
1639:Categories
953:cs.nyu.edu
873:"Taxonomy"
438:References
432:ConceptNet
414:Web mining
353:processes.
140:Bar Hillel
1645:Reasoning
1327:reasoning
958:9 January
138:In 1961,
1105:(2006).
1081:(1986).
1055:(1990).
918:Archived
727:27 March
721:Archived
696:24 March
690:Archived
688:. 2016.
686:Autoweek
639:24 March
92:avoided.
1533:Prover9
1528:Paradox
1477:F-logic
278:WordNet
214:penguin
1508:CARINE
1164:
1136:
1117:
1091:
1067:
1041:
425:OpenAI
274:canfly
266:Tweety
262:canfly
246:Tweety
238:Tweety
222:Tweety
188:Tweety
34:(AI),
1538:SPASS
1523:Otter
1518:Nqthm
1482:FO(.)
1391:CLIPS
1226:5 Nov
1006:3 May
576:3 May
541:Wired
270:robin
250:robin
230:robin
226:robin
210:robin
199:robin
192:robin
1472:CycL
1325:and
1228:2015
1162:ISBN
1134:ISBN
1115:ISBN
1089:ISBN
1065:ISBN
1039:ISBN
1008:2020
960:2018
798:help
729:2018
698:2018
641:2018
578:2020
549:2021
416:and
268:and
258:bird
256:and
254:bird
242:bird
234:bird
228:and
203:bird
1543:TPS
756:doi
664:doi
605:doi
510:doi
474:doi
428:GPT
30:In
1641::
1548:Z3
1214:.
1189:.
999:.
951:.
842:.
789::
787:}}
783:{{
752:25
750:.
746:.
719:.
715:.
684:.
658:.
627:.
601:59
599:.
595:.
569:.
557:^
539:.
506:46
504:.
468:.
446:^
420:.
1513:E
1315:e
1308:t
1301:v
1232:.
1230:.
1168:.
1142:.
1123:.
1097:.
1073:.
1047:.
1010:.
962:.
937:.
903:.
889:.
875:.
848:.
828:.
814:.
800:)
796:(
779:.
764:.
758::
731:.
700:.
670:.
666::
660:3
643:.
613:.
607::
580:.
551:.
516:.
512::
480:.
476::
216:.
205:.
194:.
20:)
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.