1104:
38:
212:, Semantic Scholar is designed to highlight the most important and influential elements of a paper. The AI technology is designed to identify hidden connections and links between research topics. Like the previously cited search engines, Semantic Scholar also exploits graph structures, which include the
192:
Another key AI-powered feature is
Research Feeds, an adaptive research recommender that uses AI to quickly learn what papers users care about reading and recommends the latest research to help scholars stay up to date. It uses a state-of-the-art paper embedding model trained using contrastive
162:. One of its aims was to address the challenge of reading numerous titles and lengthy abstracts on mobile devices. It also seeks to ensure that the three million scientific papers published yearly reach readers, since it is estimated that only half of this literature is ever read.
433:
196:
Semantic
Scholar also offers Semantic Reader, an augmented reader with the potential to revolutionize scientific reading by making it more accessible and richly contextual. Semantic Reader provides in-line citation cards that allow users to see citations with
324:
made all articles published under the
University of Chicago Press available in the Semantic Scholar corpus. At the end of 2020, Semantic Scholar had indexed 190 million papers. In 2020, Semantic Scholar reached seven million users per month.
290:
One study compared the index scope of
Semantic Scholar to Google Scholar, and found that for the papers cited by secondary studies in computer science, the two indices had comparable coverage, each only missing a handful of the papers.
590:...the publicly available corpus compiled by Semantic Scholar – a tool set up in 2015 by the Allen Institute for Artificial Intelligence in Seattle, Washington – amounting to around 200 million articles, including preprints.
960:
425:
315:
platform, was hired to lead the
Semantic Scholar project. As of August 2019, the number of included papers metadata (not the actual PDFs) had grown to more than 173 million after the addition of the
115:
to support the research process, for example by providing automatically generated summaries of scholarly papers. The
Semantic Scholar team is actively researching the use of artificial intelligence in
674:
956:
1019:
201:(short for Too Long, Didn't Read) automatically generated short summaries as they read and skimming highlights that capture key points of a paper so users can digest faster.
299:
As of
January 2018, following a 2017 project that added biomedical papers and topic summaries, the Semantic Scholar corpus included more than 40 million papers from
237:
Liu, Ying; Gayle, Albert A; Wilder-Smith, Annelies; Rocklöv, Joacim (March 2020). "The reproductive number of COVID-19 is higher compared to SARS coronavirus".
1690:
630:
165:
Artificial intelligence is used to capture the essence of a paper, generating it through an "abstractive" technique. The project uses a combination of
656:
1700:
1654:
819:
Advances in
Information Retrieval: 42nd European Conference on IR Research, ECIR 2020, Lisbon, Portugal, April 14–17, 2020, Proceedings, Part I
1639:
1482:
1131:
935:
352:
724:
459:
60:
518:
1649:
1011:
746:
1041:"The University of Chicago Press joins more than 500 publishers working with Semantic Scholar to improve search and discoverability"
957:"Tech Moves: Allen Instititue Hires Amazon Alexa Machine Learning Leader; Microsoft Chairman Takes on New Investor Role; and More"
826:
793:
220:, and the Semantic Scholar Corpus (originally a 45 million papers corpus in computer science, neuroscience and biomedicine).
817:
Jose, Joemon M.; Yilmaz, Emine; Magalhães, João; Castells, Pablo; Ferro, Nicola; Silva, Mário J.; Martins, Flávio (2020).
882:"Searching relevant papers for software engineering secondary studies: Semantic Scholar coverage and identification role"
426:"Paul Allen's AI research group unveils program that aims to shake up how we search scientific knowledge. Give it a try"
1695:
1409:
17:
1472:
1124:
851:
178:
1065:
150:
in its corpus. As of
September 2022, it includes over 200 million publications from all fields of science.
1419:
124:
989:
1669:
1664:
1634:
1117:
606:
1629:
1182:
321:
170:
116:
112:
1644:
1624:
1659:
317:
927:
1561:
1505:
104:
1601:
1317:
1273:
1066:"Semantic Scholar Adds 25 Million Scientific Papers in 2020 Through New Publisher Partnerships"
702:, Proceedings of the 16th ACM/IEEE-CS on Joint Conference on Digital Libraries - JCDL '16,
108:
720:
232:
called the
Semantic Scholar Corpus ID (abbreviated S2CID). The following entry is an example:
1591:
1566:
1343:
1252:
1164:
881:
159:
147:
128:
1581:
1546:
1500:
1388:
1348:
1333:
346:
738:
8:
1140:
1103:
1012:"AI2 joins forces with Microsoft Research to upgrade search tools for scientific studies"
760:
657:"A computer program just ranked the most influential brain scientists of the modern era"
1551:
1187:
1159:
1040:
909:
555:
550:
513:
406:
262:
213:
111:
and was publicly released in November 2015. Semantic Scholar uses modern techniques in
1607:
1495:
1462:
1283:
1204:
913:
901:
832:
822:
799:
789:
661:
574:
537:
410:
398:
334:
266:
254:
182:
631:"Allen Institute's Semantic Scholar now searches across 175 million academic papers"
559:
337: – Examination of the frequency, patterns, and graphs of citations in documents
1596:
1232:
1154:
893:
703:
666:
545:
527:
388:
383:
308:
300:
246:
186:
166:
135:
120:
1571:
1368:
1358:
1305:
1288:
1214:
1520:
1490:
1426:
1393:
1363:
1312:
1199:
1194:
928:"AI2 scales up Semantic Scholar search engine to encompass biomedical research"
697:
357:
340:
280:
205:
174:
836:
803:
393:
378:
1684:
1576:
1383:
1353:
1237:
1222:
905:
541:
402:
50:
707:
670:
312:
258:
143:
859:
532:
250:
1556:
1414:
1373:
1227:
304:
483:
279:
Semantic Scholar is free to use and unlike similar search engines (i.e.
37:
1436:
1338:
897:
379:"Artificial-intelligence institute launches free science search engine"
229:
139:
1109:
349: – Creation of knowledge from structured and unstructured sources
1457:
1300:
1530:
1525:
1452:
1242:
981:
217:
1097:
1467:
1431:
1378:
575:"Drowning in the literature? These smart software tools can help"
320:
records. In 2020, a partnership between Semantic Scholar and the
284:
193:
learning to find papers similar to those in each Library folder.
695:
1515:
1278:
1268:
209:
71:
1586:
1247:
198:
1295:
816:
236:
228:
Each paper hosted by Semantic Scholar is assigned a unique
786:
Driving Science Information Discovery in the Digital Age
103:
is a research tool for scientific literature powered by
134:
Semantic Scholar began as a database for the topics of
765:
International Journal of Language and Literary Studies
158:
Semantic Scholar provides a one-sentence summary of
821:. Cham, Switzerland: Springer Nature. p. 254.
699:
PDFFigures 2.0: Mining figures from research papers
417:
294:
360: – Quantitative study of scholarly literature
607:"AI tool summarizes lengthy papers in a sentence"
1682:
600:
598:
283:) does not search for material that is behind a
721:"Semantic Scholar | Frequently Asked Questions"
453:
451:
343: – Index of citations between publications
1125:
595:
353:List of academic databases and search engines
307:. In March 2018, Doug Raymond, who developed
460:"An AI helps you summarize the latest in AI"
448:
1691:Bibliographic databases in computer science
783:
696:Christopher Clark; Santosh Divvala (2016),
423:
61:Allen Institute for Artificial Intelligence
1132:
1118:
1102:
519:Journal of the Medical Library Association
36:
879:
856:Semantic Scholar Lab Open Research Corpus
549:
531:
392:
654:
572:
1701:Applications of artificial intelligence
1139:
648:
424:Eunjung Cha, Ariana (3 November 2015).
14:
1683:
511:
146:. In 2017, the system began including
1640:Academic databases and search engines
1113:
849:
376:
223:
1063:
739:"Semantic Scholar | Semantic Reader"
604:
573:Matthews, David (1 September 2021).
507:
505:
503:
436:from the original on 6 November 2019
322:University of Chicago Press Journals
189:, entities, and venues from papers.
1064:Dunn, Adriana (December 14, 2020).
992:from the original on 11 August 2019
749:from the original on July 15, 2023.
727:from the original on July 15, 2023.
655:Bohannon, John (11 November 2016).
457:
185:, and to extract relevant figures,
27:Search service for journal articles
24:
1410:Academic journal publishing reform
873:
788:. Chandos Publishing. p. 91.
677:from the original on 29 April 2020
214:Microsoft Academic Knowledge Graph
25:
1712:
1089:
605:Grad, Peter (November 24, 2020).
500:
458:Hao, Karen (November 18, 2020).
295:Number of users and publications
1057:
1033:
1022:from the original on 2019-08-25
1004:
974:
963:from the original on 2018-05-10
949:
938:from the original on 2018-01-19
920:
843:
810:
777:
753:
731:
713:
689:
880:Hannousse, Abdelhakim (2021).
623:
566:
512:Fricke, Suzanne (2018-01-12).
476:
370:
181:to the traditional methods of
13:
1:
1670:Category:Scientific documents
364:
153:
1665:Category:Academic publishing
784:Baykoucheva, Svetla (2021).
488:research.semanticscholar.org
7:
484:"Semantic Scholar Research"
328:
274:
171:natural language processing
117:natural language processing
113:natural language processing
10:
1717:
1483:Indexes and search engines
239:Journal of Travel Medicine
125:human–computer interaction
1696:Scholarly search services
1617:
1539:
1481:
1445:
1402:
1326:
1261:
1213:
1175:
1147:
394:10.1038/nature.2015.18703
107:. It is developed at the
80:
66:
56:
44:
35:
959:. GeekWire. 2018-05-02.
318:Microsoft Academic Graph
1660:Style/formatting guides
1562:Scholarly communication
1262:Other publication types
671:10.1126/science.aal0371
105:artificial intelligence
1602:Least publishable unit
1274:Collection of articles
852:"Open Research Corpus"
850:Ammar, Waleed (2019).
377:Jones, Nicola (2015).
272:
109:Allen Institute for AI
1592:Electronic publishing
1567:Scientific literature
1344:Article-level metrics
533:10.5195/jmla.2018.280
464:MIT Technology Review
234:
160:scientific literature
148:biomedical literature
129:information retrieval
86:; 8 years ago
84:November 2, 2015
1635:Open-access journals
1582:Open scientific data
1389:SCImago Journal Rank
1349:Author-level metrics
1334:Acknowledgment index
1045:RCNi Company Limited
347:Knowledge extraction
311:initiatives for the
216:, Springer Nature's
1630:Scientific journals
1141:Academic publishing
430:The Washington Post
251:10.1093/jtm/taaa021
224:Article identifier
32:
1650:Copyright policies
1645:University presses
1552:Scientific writing
1420:Citation advantage
1327:Impact and ranking
1160:Scientific journal
982:"Semantic Scholar"
898:10.1049/sfw2.12011
761:"Semantic Scholar"
514:"Semantic Scholar"
177:to add a layer of
30:
18:S2CID (identifier)
1678:
1677:
1655:Preprint policies
1625:Academic journals
1608:Publish or perish
1463:Version of record
1403:Reform and access
1205:Literature review
828:978-3-030-45438-8
795:978-0-12-823724-3
335:Citation analysis
204:In contrast with
183:citation analysis
179:semantic analysis
98:
97:
16:(Redirected from
1708:
1597:Ingelfinger rule
1511:Semantic Scholar
1233:Technical report
1155:Academic journal
1134:
1127:
1120:
1111:
1110:
1106:
1101:
1100:
1098:Official website
1084:
1083:
1081:
1079:
1073:Semantic Scholar
1070:
1061:
1055:
1054:
1052:
1051:
1037:
1031:
1030:
1028:
1027:
1008:
1002:
1001:
999:
997:
986:Semantic Scholar
978:
972:
971:
969:
968:
953:
947:
946:
944:
943:
924:
918:
917:
877:
871:
870:
868:
867:
858:. Archived from
847:
841:
840:
814:
808:
807:
781:
775:
774:
772:
771:
757:
751:
750:
743:Semantic Scholar
735:
729:
728:
717:
711:
710:
693:
687:
686:
684:
682:
652:
646:
645:
643:
642:
627:
621:
620:
618:
617:
602:
593:
592:
587:
585:
570:
564:
563:
553:
535:
509:
498:
497:
495:
494:
480:
474:
473:
471:
470:
455:
446:
445:
443:
441:
421:
415:
414:
396:
374:
309:machine learning
301:computer science
270:
167:machine learning
136:computer science
121:machine learning
101:Semantic Scholar
94:
92:
87:
76:
73:
40:
33:
31:Semantic Scholar
29:
21:
1716:
1715:
1711:
1710:
1709:
1707:
1706:
1705:
1681:
1680:
1679:
1674:
1613:
1572:Learned society
1535:
1477:
1441:
1398:
1369:Journal ranking
1359:Citation impact
1322:
1257:
1215:Grey literature
1209:
1171:
1143:
1138:
1096:
1095:
1092:
1087:
1077:
1075:
1068:
1062:
1058:
1049:
1047:
1039:
1038:
1034:
1025:
1023:
1010:
1009:
1005:
995:
993:
980:
979:
975:
966:
964:
955:
954:
950:
941:
939:
926:
925:
921:
878:
874:
865:
863:
848:
844:
829:
815:
811:
796:
782:
778:
769:
767:
759:
758:
754:
737:
736:
732:
719:
718:
714:
694:
690:
680:
678:
653:
649:
640:
638:
629:
628:
624:
615:
613:
603:
596:
583:
581:
571:
567:
510:
501:
492:
490:
482:
481:
477:
468:
466:
456:
449:
439:
437:
422:
418:
375:
371:
367:
331:
297:
277:
226:
156:
90:
88:
85:
72:semanticscholar
70:
57:Created by
47:
28:
23:
22:
15:
12:
11:
5:
1714:
1704:
1703:
1698:
1693:
1676:
1675:
1673:
1672:
1667:
1662:
1657:
1652:
1647:
1642:
1637:
1632:
1627:
1621:
1619:
1615:
1614:
1612:
1611:
1604:
1599:
1594:
1589:
1584:
1579:
1574:
1569:
1564:
1559:
1554:
1549:
1543:
1541:
1540:Related topics
1537:
1536:
1534:
1533:
1528:
1523:
1521:Web of Science
1518:
1513:
1508:
1503:
1498:
1493:
1491:Google Scholar
1487:
1485:
1479:
1478:
1476:
1475:
1470:
1465:
1460:
1455:
1449:
1447:
1443:
1442:
1440:
1439:
1434:
1429:
1427:Serials crisis
1424:
1423:
1422:
1412:
1406:
1404:
1400:
1399:
1397:
1396:
1394:Scientometrics
1391:
1386:
1381:
1376:
1371:
1366:
1364:Citation index
1361:
1356:
1351:
1346:
1341:
1336:
1330:
1328:
1324:
1323:
1321:
1320:
1315:
1313:Poster session
1310:
1309:
1308:
1303:
1293:
1292:
1291:
1286:
1276:
1271:
1265:
1263:
1259:
1258:
1256:
1255:
1250:
1245:
1240:
1235:
1230:
1225:
1219:
1217:
1211:
1210:
1208:
1207:
1202:
1200:Position paper
1197:
1195:Review article
1192:
1191:
1190:
1179:
1177:
1173:
1172:
1170:
1169:
1168:
1167:
1157:
1151:
1149:
1145:
1144:
1137:
1136:
1129:
1122:
1114:
1108:
1107:
1091:
1090:External links
1088:
1086:
1085:
1056:
1032:
1018:. 2018-12-05.
1003:
973:
948:
934:. 2017-10-17.
919:
892:(1): 126–146.
872:
842:
827:
809:
794:
776:
752:
730:
712:
688:
647:
622:
594:
565:
526:(1): 145–147.
499:
475:
447:
416:
368:
366:
363:
362:
361:
358:Scientometrics
355:
350:
344:
341:Citation index
338:
330:
327:
296:
293:
281:Google Scholar
276:
273:
225:
222:
206:Google Scholar
175:machine vision
155:
152:
96:
95:
82:
78:
77:
68:
64:
63:
58:
54:
53:
48:
45:
42:
41:
26:
9:
6:
4:
3:
2:
1713:
1702:
1699:
1697:
1694:
1692:
1689:
1688:
1686:
1671:
1668:
1666:
1663:
1661:
1658:
1656:
1653:
1651:
1648:
1646:
1643:
1641:
1638:
1636:
1633:
1631:
1628:
1626:
1623:
1622:
1620:
1616:
1609:
1605:
1603:
1600:
1598:
1595:
1593:
1590:
1588:
1585:
1583:
1580:
1578:
1577:Open research
1575:
1573:
1570:
1568:
1565:
1563:
1560:
1558:
1555:
1553:
1550:
1548:
1545:
1544:
1542:
1538:
1532:
1529:
1527:
1524:
1522:
1519:
1517:
1514:
1512:
1509:
1507:
1504:
1502:
1499:
1497:
1494:
1492:
1489:
1488:
1486:
1484:
1480:
1474:
1471:
1469:
1466:
1464:
1461:
1459:
1456:
1454:
1451:
1450:
1448:
1444:
1438:
1435:
1433:
1430:
1428:
1425:
1421:
1418:
1417:
1416:
1413:
1411:
1408:
1407:
1405:
1401:
1395:
1392:
1390:
1387:
1385:
1384:Impact factor
1382:
1380:
1377:
1375:
1372:
1370:
1367:
1365:
1362:
1360:
1357:
1355:
1354:Bibliometrics
1352:
1350:
1347:
1345:
1342:
1340:
1337:
1335:
1332:
1331:
1329:
1325:
1319:
1316:
1314:
1311:
1307:
1304:
1302:
1299:
1298:
1297:
1294:
1290:
1287:
1285:
1282:
1281:
1280:
1277:
1275:
1272:
1270:
1267:
1266:
1264:
1260:
1254:
1251:
1249:
1246:
1244:
1241:
1239:
1238:Annual report
1236:
1234:
1231:
1229:
1226:
1224:
1223:Working paper
1221:
1220:
1218:
1216:
1212:
1206:
1203:
1201:
1198:
1196:
1193:
1189:
1186:
1185:
1184:
1181:
1180:
1178:
1174:
1166:
1165:Public health
1163:
1162:
1161:
1158:
1156:
1153:
1152:
1150:
1146:
1142:
1135:
1130:
1128:
1123:
1121:
1116:
1115:
1112:
1105:
1099:
1094:
1093:
1074:
1067:
1060:
1046:
1042:
1036:
1021:
1017:
1013:
1007:
991:
987:
983:
977:
962:
958:
952:
937:
933:
929:
923:
915:
911:
907:
903:
899:
895:
891:
887:
883:
876:
862:on 2019-03-29
861:
857:
853:
846:
838:
834:
830:
824:
820:
813:
805:
801:
797:
791:
787:
780:
766:
762:
756:
748:
744:
740:
734:
726:
722:
716:
709:
705:
701:
700:
692:
676:
672:
668:
664:
663:
658:
651:
636:
632:
626:
612:
608:
601:
599:
591:
580:
576:
569:
561:
557:
552:
547:
543:
539:
534:
529:
525:
521:
520:
515:
508:
506:
504:
489:
485:
479:
465:
461:
454:
452:
435:
431:
427:
420:
412:
408:
404:
400:
395:
390:
386:
385:
380:
373:
369:
359:
356:
354:
351:
348:
345:
342:
339:
336:
333:
332:
326:
323:
319:
314:
310:
306:
302:
292:
288:
286:
282:
271:
268:
264:
260:
256:
252:
248:
244:
240:
233:
231:
221:
219:
215:
211:
207:
202:
200:
194:
190:
188:
184:
180:
176:
172:
168:
163:
161:
151:
149:
145:
141:
137:
132:
130:
126:
122:
118:
114:
110:
106:
102:
83:
79:
75:
69:
65:
62:
59:
55:
52:
51:Search engine
49:
43:
39:
34:
19:
1510:
1078:November 22,
1076:. Retrieved
1072:
1059:
1048:. Retrieved
1044:
1035:
1024:. Retrieved
1015:
1006:
994:. Retrieved
985:
976:
965:. Retrieved
951:
940:. Retrieved
931:
922:
889:
886:IET Software
885:
875:
864:. Retrieved
860:the original
855:
845:
818:
812:
785:
779:
768:. Retrieved
764:
755:
742:
733:
715:
698:
691:
679:. Retrieved
660:
650:
639:. Retrieved
637:. 2019-10-23
634:
625:
614:. Retrieved
610:
589:
582:. Retrieved
578:
568:
523:
517:
491:. Retrieved
487:
478:
467:. Retrieved
463:
438:. Retrieved
429:
419:
382:
372:
313:Amazon Alexa
298:
289:
278:
242:
238:
235:
227:
203:
195:
191:
164:
157:
144:neuroscience
133:
100:
99:
46:Type of site
1557:Peer review
1437:#ICanHazPDF
1415:Open access
1374:Eigenfactor
1318:Proceedings
1228:White paper
681:12 November
635:VentureBeat
611:Tech Xplore
584:5 September
440:November 3,
305:biomedicine
1685:Categories
1473:Retraction
1446:Versioning
1339:Altmetrics
1284:Biological
1050:2021-11-22
1026:2019-08-25
967:2018-05-09
942:2018-01-18
866:2024-08-05
837:1164658107
804:1241441806
770:2021-11-09
708:Q108172042
641:2021-02-16
616:2021-02-16
493:2021-11-22
469:2021-02-16
365:References
230:identifier
154:Technology
140:geoscience
91:2015-11-02
1458:Postprint
1301:Monograph
1253:Lab notes
996:11 August
914:234053002
906:1751-8814
542:1558-9439
411:182440976
403:1476-4687
267:211099356
1531:OpenAlex
1526:Paperity
1453:Preprint
1289:Chemical
1243:Pamphlet
1188:Abstract
1148:Journals
1020:Archived
1016:GeekWire
990:Archived
961:Archived
936:Archived
932:GeekWire
747:Archived
725:Archived
704:Wikidata
675:Archived
560:45802944
434:Archived
329:See also
275:Indexing
259:32052846
218:SciGraph
81:Launched
1547:Imprint
1468:Erratum
1432:Sci-Hub
1379:h-index
1306:Chapter
662:Science
551:5764585
285:paywall
89: (
1516:Scopus
1496:AMiner
1279:Patent
1269:Thesis
1176:Papers
912:
904:
835:
825:
802:
792:
706:
579:Nature
558:
548:
540:
409:
401:
384:Nature
265:
257:
210:PubMed
187:tables
173:, and
142:, and
127:, and
1618:Lists
1587:ORCID
1248:Essay
1183:Paper
1069:(PDF)
910:S2CID
556:S2CID
407:S2CID
263:S2CID
245:(2).
1506:CORE
1501:BASE
1296:Book
1080:2021
998:2019
902:ISSN
833:OCLC
823:ISBN
800:OCLC
790:ISBN
683:2016
586:2022
538:ISSN
442:2015
399:ISSN
303:and
255:PMID
208:and
199:TLDR
74:.org
894:doi
667:doi
546:PMC
528:doi
524:106
389:doi
247:doi
67:URL
1687::
1071:.
1043:.
1014:.
988:.
984:.
930:.
908:.
900:.
890:15
888:.
884:.
854:.
831:.
798:.
763:.
745:.
741:.
723:.
673:.
665:.
659:.
633:.
609:.
597:^
588:.
577:.
554:.
544:.
536:.
522:.
516:.
502:^
486:.
462:.
450:^
432:.
428:.
405:.
397:.
387:.
381:.
287:.
261:.
253:.
243:27
241:.
169:,
138:,
131:.
123:,
119:,
1610:"
1606:"
1133:e
1126:t
1119:v
1082:.
1053:.
1029:.
1000:.
970:.
945:.
916:.
896::
869:.
839:.
806:.
773:.
685:.
669::
644:.
619:.
562:.
530::
496:.
472:.
444:.
413:.
391::
269:.
249::
93:)
20:)
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.