132:
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.
141:
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.
93:" 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.
77:
401:
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
423:, 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.
324:
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.
396:
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
347:
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
310:
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
67:
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
400:
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
332:
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
140:
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.
110:
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
323:
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
153:
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
27:
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
131:
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
111:
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
353:
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
162:
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.
282:
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
48:"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."
80:
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
341:
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
269:
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.
89:" 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 "
68:
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".
265:. 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,
315:, 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.
1295:
278:
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:
709:
1149:
Hageback, Niklas. (2017). The
Virtual Mind: Designing the Logic to Approximate Human Thinking (Chapman & Hall/CRC Artificial Intelligence and Robotics Series) 1st Edition.
678:
397:
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 .
388:
data is insufficient to produce an artificial general intelligence capable of commonsense reasoning, and have therefore turned to less-supervised learning techniques.
96:
Overlapping subtopics of commonsense reasoning include quantities and measurements, time and space, physics, minds, society, plans and goals, and actions and change.
311:
than Haydn. The inferences involved reduce themselves to solving systems of linear inequalities. To integrate that kind of reasoning with concrete purposes, such as
515:
Matuszek, Cynthia, et al. "Searching for common sense: Populating cyc from the web." UMBC Computer
Science and Electrical Engineering Department Collection (2005).
479:
McCarthy, John. "Artificial intelligence, logic and formalizing common sense." Philosophical logic and artificial intelligence. Springer, Dordrecht, 1989. 161-190.
454:
289:
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.
971:
154:
one. Such tasks seem obvious when an individual possesses simple commonsense reasoning, but to ensure that a robot will avoid such mistakes is challenging.
85:
Compared with humans, existing AI lacks several features of human commonsense reasoning; most notably, humans have powerful mechanisms for reasoning about "
363:
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.
1200:
372:
Compared with humans, as of 2018 existing computer programs perform extremely poorly on modern "commonsense reasoning" benchmark tests such as the
848:
613:
105:
51:"Commonsense knowledge differs from encyclopedic knowledge in that it deals with general knowledge rather than the details of specific entities."
1009:
Bosselut, Antoine, et al. "Comet: Commonsense transformers for automatic knowledge graph construction." arXiv preprint arXiv:1906.05317 (2019).
54:
Commonsense knowledge is "real world knowledge that can provide a basis for additional knowledge to be gathered and interpreted automatically".
1302:
63:
Common sense is "broadly reusable background knowledge that's not specific to a particular subject area... knowledge that you ought to have."
913:." International Conference on Knowledge-Based and Intelligent Information and Engineering Systems. Springer, Berlin, Heidelberg, 2004.
119:. To perform them, the machine has to be aware of the same concepts that an individual, who possess commonsense knowledge, recognizes.
923:
906:
985:
1311:
701:
670:
1146:| Encyclopedia.com: FREE online dictionary. Available at: http://www.encyclopedia.com/doc/1O88-commonsenseknowledge.html .
1154:
1126:
1041:
489:
Tandon, Niket; Varde, Aparna S.; de Melo, Gerard (22 February 2018). "Commonsense
Knowledge in Machine Intelligence".
1579:
1107:
1081:
1057:
1031:
358:. It takes different forms that include using unreliable data and rules, whose conclusions are not certain sometimes.
525:
381:
376:. The problem of attaining human-level competency at "commonsense knowledge" tasks is considered to probably be "
1569:
312:
305:
1404:
1638:
1559:
1475:
1389:
1288:
555:
1455:
1432:
1384:
1236:
814:
368:
Fifth, when formulating presumptions it is challenging to discern and determine the level of abstraction.
171:
Taxonomy is the collection of individuals and categories and their relations. Three basic relations are:
1208:
621:
60:
Common sense is "all the knowledge about the world that we take for granted but rarely state out loud".
961:
Yampolskiy, Roman V. "AI-Complete, AI-Hard, or AI-Easy-Classification of
Problems in AI." MAICS. 2012.
1602:
1412:
373:
1098:
The
Emotion Machine: Commonsense Thinking, Artificial Intelligence, and the Future of the Human Mind
786:
1516:
937:
828:
702:"Boston may be famous for bad drivers, but it's the testing ground for a smarter self-driving car"
1546:
861:
20:
1175:
765:
1597:
1554:
1531:
1511:
1417:
1176:
CYC: Using Common Sense
Knowledge to Overcome Brittleness and Knowledge Acquisition Bottlenecks
1071:
337:, five major obstacles interfere with the producing of a satisfactory "commonsense reasoner".
1480:
1361:
1346:
773:
800:
1612:
1592:
1422:
1331:
1139:. Available at: https://www.edx.org/course/artificial-intelligence-uc-berkeleyx-cs188-1x .
903:
57:
The commonsense world consists of "time, space, physical interactions, people, and so on".
8:
1394:
1315:
1280:
875:
385:
355:
128:
76:
1633:
1501:
1275:
1020:
112:
44:
Some definitions and characterizations of common sense from different authors include:
1196:. Available at: http://psych.utoronto.ca/users/reingold/courses/ai/commonsense.html .
1164:. Elsevier. Available at: http://www.journals.elsevier.com/artificial-intelligence/ .
295:
The relevant state of the world at the beginning is either known or can be calculated.
1607:
1564:
1536:
1447:
1427:
1326:
1150:
1122:
1103:
1096:
1077:
1053:
1046:
1027:
656:
889:
1351:
1341:
1260:
744:
652:
593:
498:
462:
150:
1228:. Available at: https://www.theguardian.com/technology/artificialintelligenceai .
86:
1587:
1356:
1186:
910:
833:
90:
29:
16:
Branch of artificial intelligence aiming to create AI systems with "common sense"
1270:
406:
749:
732:
32:(humans' innate ability to reason about people's behavior and intentions) and
1627:
1371:
1091:
1067:
851:." Proceedings of the IEEE international conference on computer vision. 2015.
419:
language model architecture and existing commonsense knowledge bases such as
33:
502:
455:"Commonsense Reasoning and Commonsense Knowledge in Artificial Intelligence"
1437:
377:
334:
116:
175:
An individual is an instance of a category. For example, the individual
1276:
Knowledge
Infusion: In Pursuit of Robustness in Artificial Intelligence
420:
402:
1237:
https://www.udacity.com/course/intro-to-artificial-intelligence--cs271
598:
581:
733:"On the problem of making autonomous vehicles conform to traffic law"
671:"Don't worry: Autonomous cars aren't coming tomorrow (or next year)"
466:
1255:
643:
Winograd, Terry (January 1972). "Understanding natural language".
1521:
1465:
986:"Computers Already Learn From Us. But Can They Teach Themselves?"
829:"Bar Hillel Artificial Intelligence Research Machine Translation"
380:" (that is, solving it would require the ability to synthesize a
327:
266:
1496:
413:
157:
1526:
1506:
1470:
1379:
1171:. Available at: http://www.leaderu.com/truth/2truth07.html .
416:
1194:
Artificial
Intelligence | The Common Sense Knowledge Problem
1460:
1265:
1233:
Intro to
Artificial Intelligence Course and Training Online
582:"Logical Formalizations of Commonsense Reasoning: A Survey"
28:
capable of drawing conclusions that are similar to humans'
1310:
1245:. Available at: http://www.w3.org/People/Raggett/Sense/ .
1121:(2nd ed.). Waltham, Mass.: Morgan Kaufmann/Elsevier.
292:
There is a single actor and all events are their actions.
209:
Transitivity is one type of inference in taxonomy. Since
1226:
Artificial intelligence (AI) | Technology | The Guardian
1187:
Common Sense, the Turing Test, and the Quest for Real AI
526:"How to Teach Artificial Intelligence Some Common Sense"
1119:
Commonsense Reasoning: An Event Calculus Based Approach
452:
36:(humans' natural understanding of the physical world).
348:
be represented in a form that is usable by computers.
149:
The need and importance of commonsense reasoning in
39:
1142:Encyclopedia.com, (2015). "commonsense knowledge."
122:
1095:
1045:
1019:
904:Commonsense reasoning in and over natural language
488:
233:. Inheritance is another type of inference. Since
186:One category is a subset of another. For instance
1271:The Epilog project at the University of Rochester
1169:ARTIFICIAL INTELLIGENCE AS COMMON SENSE KNOWLEDGE
614:"Cultivating Common Sense | DiscoverMagazine.com"
1625:
1174:Lenat, D., Prakash, M. and Shepherd, M. (1985).
99:
71:
970:Andrich, C, Novosel, L, and Hrnkas, B. (2009).
106:Commonsense knowledge (artificial intelligence)
448:
446:
444:
442:
440:
438:
436:
328:Challenges in automating commonsense reasoning
1296:
1201:"CommonSense - Knowledge Management Overview"
461:. Vol. 58, no. 9. pp. 92–103.
333:understanding. According to Ernest Davis and
286:Every single change is a result of some event
876:"Action and change in Commonsense reasoning"
391:
158:Successes in automated commonsense reasoning
586:Journal of Artificial Intelligence Research
433:
1303:
1289:
1266:Media Lab Commonsense Computing Initiative
197:Two categories are disjoint. For instance
974:. Information Search and Retrieval, 2009.
748:
597:
1040:
1022:Representations of Commonsense Reasoning
763:
642:
549:
547:
318:
75:
1116:
730:
144:
1626:
1090:
1066:
1026:. San Mateo, Calif.: Morgan Kaufmann.
815:"Artificial intelligence applications"
699:
553:
166:
1284:
1017:
983:
579:
544:
299:
273:
766:"Logic and Artificial Intelligence"
712:from the original on 22 August 2020
13:
1261:Commonsense Reasoning Problem Page
801:"Artificial intelligence Programs"
681:from the original on 25 March 2018
453:Ernest Davis; Gary Marcus (2015).
412:COMET (2019), which uses both the
135:
14:
1650:
1249:
764:Thomason, Richmond (2003-08-27).
731:Prakken, Henry (31 August 2017).
556:"Common Sense Comes to Computers"
384:). Some researchers believe that
40:Definitions and characterizations
1102:. New York: Simon and Schuster.
1076:. New York: Simon and Schuster.
984:Smith, Craig S. (8 April 2020).
580:Davis, Ernest (25 August 2017).
123:Commonsense in intelligent tasks
1003:
977:
964:
955:
938:"The Winograd Schema Challenge"
930:
916:
896:
882:
868:
854:
841:
821:
807:
793:
757:
737:Artificial Intelligence and Law
724:
693:
663:
313:natural language interpretation
179:is an instance of the category
1256:Commonsense Reasoning Web Site
849:Vqa: Visual question answering
636:
606:
573:
554:Pavlus, John (30 April 2020).
518:
509:
482:
473:
1:
426:
100:Commonsense knowledge problem
72:Commonsense reasoning problem
1560:Constraint logic programming
1476:Knowledge Interchange Format
1433:Procedural reasoning systems
1390:Expert systems for mortgages
1385:Connectionist expert systems
902:Liu, Hugo, and Push Singh. "
657:10.1016/0010-0285(72)90002-3
7:
1456:Attempto Controlled English
1243:Computers with Common Sense
1192:Psych.utoronto.ca, (2015).
10:
1655:
847:Antol, Stanislaw, et al. "
306:Spatial–temporal reasoning
303:
115:, machine translation and
103:
1603:Preference-based planning
1578:
1545:
1489:
1446:
1403:
1370:
1322:
1160:Intelligence, A. (2015).
1144:A Dictionary of Sociology
1117:Mueller, Erik T. (2015).
750:10.1007/s10506-017-9210-0
459:Communications of the ACM
392:Approaches and techniques
374:Winograd Schema Challenge
1312:Knowledge representation
1052:. Norwood, N.J.: Ablex.
1048:Formalizing Common Sense
382:human-level intelligence
249:is marked with property
1547:Constraint satisfaction
1162:Artificial Intelligence
1137:Artificial Intelligence
924:"Qualitative reasoning"
503:10.1145/3186549.3186562
241:, which is a subset of
21:artificial intelligence
1598:Partial-order planning
1555:Constraint programming
1224:the Guardian, (2015).
1207:. 2015. Archived from
1018:Davis, Ernest (1990).
972:Common Sense Knowledge
781:Cite journal requires
620:. 2017. Archived from
82:
1481:Web Ontology Language
1423:Deductive classifiers
1362:Knowledge engineering
1347:Model-based reasoning
1337:Commonsense reasoning
1231:Udacity.com, (2015).
1185:Levesque, H. (2017).
1167:Leaderu.com, (2015).
706:MIT Technology Review
700:Knight, Will (2017).
319:Qualitative reasoning
304:Further information:
79:
25:commonsense reasoning
1613:State space planning
1593:Multi-agent planning
1395:Legal expert systems
1332:Case-based reasoning
890:"Temporal reasoning"
645:Cognitive Psychology
145:Robotic manipulation
1639:Automated reasoning
1182:, 6(4), p. 65.
1073:The Society of Mind
386:supervised learning
356:non-monotonic logic
167:Taxonomic reasoning
1580:Automated planning
1448:Ontology languages
1418:Constraint solvers
990:The New York Times
909:2017-08-09 at the
532:. 13 November 2018
300:Temporal reasoning
253:, it follows that
237:is an instance of
229:is an instance of
225:, it follows that
213:is an instance of
113:object recognition
83:
1621:
1620:
1608:Reactive planning
1565:Local consistency
1405:Reasoning systems
1352:Inference engines
1327:Backward chaining
1235:. Available at:
1205:Sensesoftware.com
618:Discover Magazine
599:10.1613/jair.5339
491:ACM SIGMOD Record
274:Action and change
201:is disjoint from
151:autonomous robots
1646:
1357:Proof assistants
1342:Forward chaining
1305:
1298:
1291:
1282:
1281:
1241:W3.org, (2015).
1220:
1218:
1216:
1132:
1113:
1101:
1087:
1063:
1051:
1037:
1025:
1010:
1007:
1001:
1000:
998:
996:
981:
975:
968:
962:
959:
953:
952:
950:
948:
934:
928:
927:
920:
914:
900:
894:
893:
886:
880:
879:
872:
866:
865:
858:
852:
845:
839:
838:
825:
819:
818:
811:
805:
804:
797:
791:
790:
784:
779:
777:
769:
761:
755:
754:
752:
728:
722:
721:
719:
717:
697:
691:
690:
688:
686:
667:
661:
660:
640:
634:
633:
631:
629:
624:on 25 March 2018
610:
604:
603:
601:
577:
571:
570:
568:
566:
551:
542:
541:
539:
537:
522:
516:
513:
507:
506:
486:
480:
477:
471:
470:
450:
1654:
1653:
1649:
1648:
1647:
1645:
1644:
1643:
1624:
1623:
1622:
1617:
1588:Motion planning
1574:
1541:
1490:Theorem provers
1485:
1442:
1413:Theorem provers
1399:
1366:
1318:
1309:
1252:
1214:
1212:
1211:on 17 July 2015
1199:
1129:
1110:
1084:
1060:
1034:
1014:
1013:
1008:
1004:
994:
992:
982:
978:
969:
965:
960:
956:
946:
944:
936:
935:
931:
922:
921:
917:
911:Wayback Machine
901:
897:
888:
887:
883:
874:
873:
869:
860:
859:
855:
846:
842:
834:TheGuardian.com
827:
826:
822:
813:
812:
808:
799:
798:
794:
782:
780:
771:
770:
762:
758:
729:
725:
715:
713:
698:
694:
684:
682:
669:
668:
664:
641:
637:
627:
625:
612:
611:
607:
578:
574:
564:
562:
560:Quanta Magazine
552:
545:
535:
533:
524:
523:
519:
514:
510:
487:
483:
478:
474:
467:10.1145/2701413
451:
434:
429:
394:
330:
321:
308:
302:
276:
221:is a subset of
190:is a subset of
169:
160:
147:
138:
136:Computer vision
125:
108:
102:
91:folk psychology
74:
42:
30:folk psychology
17:
12:
11:
5:
1652:
1642:
1641:
1636:
1619:
1618:
1616:
1615:
1610:
1605:
1600:
1595:
1590:
1584:
1582:
1576:
1575:
1573:
1572:
1567:
1562:
1557:
1551:
1549:
1543:
1542:
1540:
1539:
1534:
1529:
1524:
1519:
1514:
1509:
1504:
1499:
1493:
1491:
1487:
1486:
1484:
1483:
1478:
1473:
1468:
1463:
1458:
1452:
1450:
1444:
1443:
1441:
1440:
1435:
1430:
1428:Logic programs
1425:
1420:
1415:
1409:
1407:
1401:
1400:
1398:
1397:
1392:
1387:
1382:
1376:
1374:
1372:Expert systems
1368:
1367:
1365:
1364:
1359:
1354:
1349:
1344:
1339:
1334:
1329:
1323:
1320:
1319:
1308:
1307:
1300:
1293:
1285:
1279:
1278:
1273:
1268:
1263:
1258:
1251:
1250:External links
1248:
1247:
1246:
1239:
1229:
1222:
1197:
1190:
1183:
1172:
1165:
1158:
1155:978-1138054035
1147:
1140:
1133:
1128:978-0128014165
1127:
1114:
1108:
1092:Minsky, Marvin
1088:
1082:
1068:Minsky, Marvin
1064:
1058:
1042:McCarthy, John
1038:
1032:
1012:
1011:
1002:
976:
963:
954:
929:
915:
895:
881:
867:
853:
840:
820:
806:
792:
783:|journal=
756:
743:(3): 341–363.
723:
692:
662:
635:
605:
572:
543:
517:
508:
481:
472:
431:
430:
428:
425:
407:Crowd sourcing
393:
390:
370:
369:
365:
364:
360:
359:
350:
349:
344:
343:
329:
326:
320:
317:
301:
298:
297:
296:
293:
290:
287:
284:
275:
272:
261:have property
207:
206:
195:
184:
168:
165:
159:
156:
146:
143:
137:
134:
124:
121:
104:Main article:
101:
98:
73:
70:
65:
64:
61:
58:
55:
52:
49:
41:
38:
15:
9:
6:
4:
3:
2:
1651:
1640:
1637:
1635:
1632:
1631:
1629:
1614:
1611:
1609:
1606:
1604:
1601:
1599:
1596:
1594:
1591:
1589:
1586:
1585:
1583:
1581:
1577:
1571:
1568:
1566:
1563:
1561:
1558:
1556:
1553:
1552:
1550:
1548:
1544:
1538:
1535:
1533:
1530:
1528:
1525:
1523:
1520:
1518:
1515:
1513:
1510:
1508:
1505:
1503:
1500:
1498:
1495:
1494:
1492:
1488:
1482:
1479:
1477:
1474:
1472:
1469:
1467:
1464:
1462:
1459:
1457:
1454:
1453:
1451:
1449:
1445:
1439:
1436:
1434:
1431:
1429:
1426:
1424:
1421:
1419:
1416:
1414:
1411:
1410:
1408:
1406:
1402:
1396:
1393:
1391:
1388:
1386:
1383:
1381:
1378:
1377:
1375:
1373:
1369:
1363:
1360:
1358:
1355:
1353:
1350:
1348:
1345:
1343:
1340:
1338:
1335:
1333:
1330:
1328:
1325:
1324:
1321:
1317:
1313:
1306:
1301:
1299:
1294:
1292:
1287:
1286:
1283:
1277:
1274:
1272:
1269:
1267:
1264:
1262:
1259:
1257:
1254:
1253:
1244:
1240:
1238:
1234:
1230:
1227:
1223:
1210:
1206:
1202:
1198:
1195:
1191:
1188:
1184:
1181:
1177:
1173:
1170:
1166:
1163:
1159:
1156:
1152:
1148:
1145:
1141:
1138:
1135:edX, (2014).
1134:
1130:
1124:
1120:
1115:
1111:
1109:0-7432-7663-9
1105:
1100:
1099:
1093:
1089:
1085:
1083:0-671-60740-5
1079:
1075:
1074:
1069:
1065:
1061:
1059:1-871516-49-8
1055:
1050:
1049:
1043:
1039:
1035:
1033:1-55860-033-7
1029:
1024:
1023:
1016:
1015:
1006:
991:
987:
980:
973:
967:
958:
943:
939:
933:
925:
919:
912:
908:
905:
899:
891:
885:
877:
871:
863:
857:
850:
844:
836:
835:
830:
824:
816:
810:
802:
796:
788:
775:
767:
760:
751:
746:
742:
738:
734:
727:
711:
707:
703:
696:
680:
676:
672:
666:
658:
654:
650:
646:
639:
623:
619:
615:
609:
600:
595:
591:
587:
583:
576:
561:
557:
550:
548:
531:
527:
521:
512:
504:
500:
496:
492:
485:
476:
468:
464:
460:
456:
449:
447:
445:
443:
441:
439:
437:
432:
424:
422:
418:
415:
410:
408:
404:
398:
389:
387:
383:
379:
375:
367:
366:
362:
361:
357:
352:
351:
346:
345:
340:
339:
338:
336:
325:
316:
314:
307:
294:
291:
288:
285:
281:
280:
279:
271:
268:
264:
260:
256:
252:
248:
244:
240:
236:
232:
228:
224:
220:
216:
212:
204:
200:
196:
193:
189:
185:
182:
178:
174:
173:
172:
164:
155:
152:
142:
133:
130:
120:
118:
114:
107:
97:
94:
92:
88:
87:naĂŻve physics
78:
69:
62:
59:
56:
53:
50:
47:
46:
45:
37:
35:
34:naive physics
31:
26:
22:
1438:Rule engines
1336:
1242:
1232:
1225:
1213:. Retrieved
1209:the original
1204:
1193:
1189:. MIT Press.
1179:
1168:
1161:
1143:
1136:
1118:
1097:
1072:
1047:
1021:
1005:
993:. Retrieved
989:
979:
966:
957:
945:. Retrieved
941:
932:
918:
898:
884:
870:
856:
843:
832:
823:
809:
795:
774:cite journal
759:
740:
736:
726:
714:. Retrieved
705:
695:
683:. Retrieved
674:
665:
651:(1): 1–191.
648:
644:
638:
626:. Retrieved
622:the original
617:
608:
589:
585:
575:
563:. Retrieved
559:
534:. Retrieved
529:
520:
511:
497:(4): 49–52.
494:
490:
484:
475:
458:
411:
399:
395:
371:
331:
322:
309:
277:
262:
258:
254:
250:
246:
242:
238:
234:
230:
226:
222:
218:
214:
210:
208:
202:
198:
191:
187:
180:
176:
170:
161:
148:
139:
126:
109:
95:
84:
66:
43:
24:
18:
1570:SMT solvers
1180:AI Magazine
592:: 651–723.
536:11 February
378:AI complete
335:Gary Marcus
283:(progress).
117:text mining
1628:Categories
942:cs.nyu.edu
862:"Taxonomy"
427:References
421:ConceptNet
403:Web mining
342:processes.
129:Bar Hillel
1634:Reasoning
1316:reasoning
947:9 January
127:In 1961,
1094:(2006).
1070:(1986).
1044:(1990).
907:Archived
716:27 March
710:Archived
685:24 March
679:Archived
677:. 2016.
675:Autoweek
628:24 March
81:avoided.
1522:Prover9
1517:Paradox
1466:F-logic
267:WordNet
203:penguin
1497:CARINE
1153:
1125:
1106:
1080:
1056:
1030:
414:OpenAI
263:canfly
255:Tweety
251:canfly
235:Tweety
227:Tweety
211:Tweety
177:Tweety
23:(AI),
1527:SPASS
1512:Otter
1507:Nqthm
1471:FO(.)
1380:CLIPS
1215:5 Nov
995:3 May
565:3 May
530:Wired
259:robin
239:robin
219:robin
215:robin
199:robin
188:robin
181:robin
1461:CycL
1314:and
1217:2015
1151:ISBN
1123:ISBN
1104:ISBN
1078:ISBN
1054:ISBN
1028:ISBN
997:2020
949:2018
787:help
718:2018
687:2018
630:2018
567:2020
538:2021
405:and
257:and
247:bird
245:and
243:bird
231:bird
223:bird
217:and
192:bird
1532:TPS
745:doi
653:doi
594:doi
499:doi
463:doi
417:GPT
19:In
1630::
1537:Z3
1203:.
1178:.
988:.
940:.
831:.
778::
776:}}
772:{{
741:25
739:.
735:.
708:.
704:.
673:.
647:.
616:.
590:59
588:.
584:.
558:.
546:^
528:.
495:46
493:.
457:.
435:^
409:.
1502:E
1304:e
1297:t
1290:v
1221:.
1219:.
1157:.
1131:.
1112:.
1086:.
1062:.
1036:.
999:.
951:.
926:.
892:.
878:.
864:.
837:.
817:.
803:.
789:)
785:(
768:.
753:.
747::
720:.
689:.
659:.
655::
649:3
632:.
602:.
596::
569:.
540:.
505:.
501::
469:.
465::
205:.
194:.
183:.
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.