Jump to content

Semantic Scholar: Difference between revisions

From Wikipedia, the free encyclopedia
Browse history interactively
← Previous editNext edit →
Content deleted Content added
VisualWikitext
No edit summary
Tags: Reverted section blanking Mobile edit Mobile web edit
No edit summary
Tags: Reverted Mobile edit Mobile web edit
Line 5: Line 5:
| type = [[Search engine]]
| type = [[Search engine]]
| author = [[Allen Institute for Artificial Intelligence]]
| author = [[Allen Institute for Artificial Intelligence]]
| launch_date = {{Start date and age|2015|11|2}}<ref>{{
| launch_date = {{Start date and age|2015|11|2}}<ref>{{cite journal|last1=Jones|first1=Nicola|title=Artificial-intelligence institute launches free science search engine|journal=[[Nature (journal)|Nature]]|year=2015|issn=1476-4687|doi=10.1038/nature.2015.18703|s2cid=182440976 |doi-access=free}}</ref>
| website = {{URL|https://semanticscholar.org}}
}}
}}

'''Semantic Scholar''' is a research tool for scientific literature powered by [[artificial intelligence]]. It is developed at the [[Allen Institute for AI]] and was publicly released in November 2015.<ref name="Eunjung Cha 3Nov2015">{{Cite news |first1=Ariana |last1=Eunjung Cha |date=3 November 2015 |title=Paul Allen's AI research group unveils program that aims to shake up how we search scientific knowledge. Give it a try. |url=https://www.washingtonpost.com/news/to-your-health/wp/2015/11/02/paul-allens-ai-research-group-unveils-program-that-aims-to-shake-up-how-we-search-scientific-knowledge-give-it-a-try/ |url-status=live |archive-url=https://web.archive.org/web/20191106162910/https://www.washingtonpost.com/news/to-your-health/wp/2015/11/02/paul-allens-ai-research-group-unveils-program-that-aims-to-shake-up-how-we-search-scientific-knowledge-give-it-a-try/ |archive-date=6 November 2019 |access-date=November 3, 2015 |newspaper=The Washington Post}}</ref> Semantic Scholar uses modern techniques in [[natural language processing]] to support the research process, for example by providing automatically generated summaries of scholarly papers.<ref name="Hao 18Nov2020">{{Cite web |last=Hao |first=Karen |date=November 18, 2020 |title=An AI helps you summarize the latest in AI |url=https://www.technologyreview.com/2020/11/18/1012259/ai-summarizes-science-papers-ai2-semantic-scholar/ |access-date=2021-02-16 |website=MIT Technology Review |language=en}}</ref> The Semantic Scholar team is actively researching the use of artificial intelligence in [[natural language processing]], [[machine learning]], [[human–computer interaction]], and [[information retrieval]].<ref>{{Cite web|title=Semantic Scholar Research|url=https://research.semanticscholar.org/|access-date=2021-11-22|website=research.semanticscholar.org}}</ref>

Semantic Scholar began as a database for the topics of [[computer science]], [[geoscience]], and [[neuroscience]].<ref name=":0">{{Cite journal |last=Fricke|first=Suzanne|date=2018-01-12|title=Semantic Scholar|journal=[[Journal of the Medical Library Association]]|language=en|volume=106|issue=1|pages=145–147|doi=10.5195/jmla.2018.280|s2cid=45802944|issn=1558-9439|doi-access=free|pmc=5764585}}</ref> In 2017, the system began including [[biomedical literature]] in its corpus.<ref name=":0" /> {{As of|2022|Sep}}, it includes over 200 million publications from all fields of science.<ref>{{cite news |last1=Matthews |first1=David |title=Drowning in the literature? These smart software tools can help |url=https://www.nature.com/articles/d41586-021-02346-4 |access-date=5 September 2022 |work=Nature |date=1 September 2021 |quote=...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.}}</ref>


== Technology ==
== Technology ==

Revision as of 05:50, 26 September 2024

{{Infobox website | name = Semantic Scholar | logo = Semantic Scholar logo.svg | type = Search engine | author = Allen Institute for Artificial Intelligence | launch_date = November 2, 2015; 9 years ago (2015-11-02)Cite error: A <ref> tag is missing the closing </ref> (see the help page). 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.[1]

Artificial intelligence is used to capture the essence of a paper, generating it through an "abstractive" technique.[2] The project uses a combination of machine learning, natural language processing, and machine vision to add a layer of semantic analysis to the traditional methods of citation analysis, and to extract relevant figures, tables, entities, and venues from papers.[3][4]

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 learning to find papers similar to those in each Library folder.[5]

Semantic Scholar also offers Semantic Reader, an augmented reader with the potential to revolutionize scientific reading by making it more accessible and richly contextual.[6] Semantic Reader provides in-line citation cards that allow users to see citations with TLDR (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.

In contrast with Google Scholar and PubMed, Semantic Scholar is designed to highlight the most important and influential elements of a paper.[7] The AI technology is designed to identify hidden connections and links between research topics.[8] Like the previously cited search engines, Semantic Scholar also exploits graph structures, which include the Microsoft Academic Knowledge Graph, Springer Nature's SciGraph, and the Semantic Scholar Corpus (originally a 45 million papers corpus in computer science, neuroscience and biomedicine).[9][10]

Indexing

Semantic Scholar is free to use and unlike similar search engines (i.e. Google Scholar) does not search for material that is behind a aywall.[11][citation needed]

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.[11]

See also

References

  1. ^ "Allen Institute's Semantic Scholar now searches across 175 million academic papers". VentureBeat. 2019-10-23. Retrieved 2021-02-16.
  2. ^ Cite error: The named reference Hao 18Nov2020 was invoked but never defined (see the help page).
  3. ^ Bohannon, John (11 November 2016). "A computer program just ranked the most influential brain scientists of the modern era". Science. doi:10.1126/science.aal0371. Archived from the original on 29 April 2020. Retrieved 12 November 2016.
  4. ^ Christopher Clark; Santosh Divvala (2016), PDFFigures 2.0: Mining figures from research papers, Proceedings of the 16th ACM/IEEE-CS on Joint Conference on Digital Libraries - JCDL '16, Wikidata Q108172042
  5. ^ "Semantic Scholar | Frequently Asked Questions". Archived from the original on July 15, 2023.
  6. ^ "Semantic Scholar | Semantic Reader". Semantic Scholar. Archived from the original on July 15, 2023.
  7. ^ "Semantic Scholar". International Journal of Language and Literary Studies. Retrieved 2021-11-09.
  8. ^ Baykoucheva, Svetla (2021). Driving Science Information Discovery in the Digital Age. Chandos Publishing. p. 91. ISBN 978-0-12-823724-3. OCLC 1241441806.
  9. ^ Jose, Joemon M.; Yilmaz, Emine; Magalhães, João; Castells, Pablo; Ferro, Nicola; Silva, Mário J.; Martins, Flávio (2020). Advances in Information Retrieval: 42nd European Conference on IR Research, ECIR 2020, Lisbon, Portugal, April 14–17, 2020, Proceedings, Part I. Cham, Switzerland: Springer Nature. p. 254. ISBN 978-3-030-45438-8. OCLC 1164658107.
  10. ^ Ammar, Waleed (2019). "Open Research Corpus". Semantic Scholar Lab Open Research Corpus. Archived from the original on 2019-03-29. Retrieved 2024-08-05.
  11. ^ a b Ha, Abdlhakm (2021). 15 (2). doi:10.1049/sfw2.12011. ISSN 0. {{cite journal}}: Check |issn= value (help); Cite journal requires |journal= (help); Missing or empty |title= (help); Unknown parameter |c2cid= ignored (help)
Wikidata has the properties: 
Official website Edit this at Wikidata

{{}}


[[]] [[]] [[]]

Retrieved from "https://en.wikipedia.org/w/index.php?title=Semantic_Scholar&oldid=1247821561"