Semantic Scholar - Estado da Arte

 

Vídeo -> https://youtu.be/FUVxIIfXSUo

Semantic Scholar is an AI-powered search and discovery tool used by millions of scholars globally each month, and supports hundreds of thousands of scholarly searches each week. 

Our mission is to empower researchers to fight information overload. Searching on our platform enables scholars to navigate through hundreds of millions of papers in all scientific domains. 

So, how does it work? Underlying all of Semantic Scholar is a deep semantic analytic engine that helps researchers understand the meaning of a paper. Natural language processing and machine learning models rank the results by relevance, all to help you quickly find the most up-to-date research in your field. 

To get started, visit semanticscholar.org and enter a search for a paper, author, topic, or keyword. You can further refine your search results using our many filter options. Select field of study to find literature from a particular domain. If you're looking for recent research, filter your results down to the past two years. You can also filter by publication type, authors, or journals and conferences. 

Clicking on a paper title will take you to our paper pages.

Vídeo -> https://youtu.be/III9TER1yNA

Semantic Scholar is a free, AI-powered research tool for scientific literature used by more than 8 million scholars globally. With nearly 200 million papers across all scientific domains, 

Semantic Scholar provides professional scholars like researchers, engineers, clinicians, and scientists with free, AI-powered tools to quickly find the research that is most relevant to their work. 

To get started, visit semanticscholar.org and search for a paper, author, topic, or keyword. You can filter by field, date range, conference, and more to refine the search results as well as sort by relevance or recency. 

On a paper page, you can browse videos, presentations, code libraries, and clinical trials. Get a glimpse at a paper’s figures, tables, and topics, skim news or blog articles discussing a paper, and navigate citations and references to find connections to other papers. 

Our system indexes citations for millions of publications, using AI models to classify the intent and predict the influence of each. 

With a free account, you can save papers for later reading, create an alert to get email notifications for a paper, cite the paper, or launch a research feed for new recommendations based on your ratings.

Vídeo ->  https://youtu.be/WAefQlDN5mI

With billions of citations, Semantic Scholar provides a citation graph that allows scholars to navigate and discover the most relevant research across all fields of study. We offer many ways to explore our citation graph, including our novel method of classifying citations by type and influence, as well as searching citations. 

Our system indexes billions of citations, using AI models to classify the intent and predict the influence of each. 

We’ve identified three classification types; cites background, cites methods, and cites results. You can find citation type by scrolling to the citations listed for any paper and using the citation type filter to identify papers that cites background, cites methods, or cites results. 

While many citations are incidental, Semantic Scholar classifies some citations as being “Highly Influential,” allowing scholars to quickly determine which publications to read in depth. Find highly influenced citations sorting by Most Influenced Papers or scanning for the Highly Influenced paper badge under each paper title. 

Searching citations of a paper helps researchers quickly navigate through a large list of citations and narrow results down to the most relevant.

Vídeo -> https://youtu.be/7s8JbeQrk8Y

Our TLDR feature generates single-sentence paper summaries in search results so you can quickly decide which papers to read in full. The new TLDR feature in Semantic Scholar puts automatically generated single-sentence paper summaries right on the search results page

S2ORC: The Semantic Scholar Open Research Corpus

A large, open-access corpus of academic literature across many disciplines with paper metadata, structured full text and citation links.  

Download Corpus -> https://github.com/allenai/s2orc

Apresentação-> https://slideslive.com/38929131/s2orc-the-semantic-scholar-open-research-corpus

Sobre o Semantic Scholar no Journal of the Medical Library Association

 

Fonte: DOI: dx.doi.org/10.5195/jmla.2018.280

 

Eagerly awaited by researchers for years, concrete examples of artificial intelligence–enabled search
engines are beginning to emerge.  Searches that return tens of thousands of results in Google Scholar
and thousands in PubMed return a few hundred in Semantic Scholar, all directly relevant. Semantic
Scholar removes the long tail of search results, allowing one to quickly get up to speed on one’s
disciplines, while limiting the distraction caused by less relevant research. 

 

Favoring simplicity of interface, Semantic Scholar offers only a few options for refining and sorting
search results. It sorts only by relevance and publication date. While it does allow truncation, it does not
support Boolean or phrase searching. 

 

Other artificial intelligence–enabled search engines exist. Some have compared Semantic Scholar to
the Memex project from NASA and DARPA [6] that searches the deep web, though that project is not
available to the public. It is also compared to Meta [7], now owned by the Chan-Zuckerburg Initiative.
Meta was designed in 2010 with a greater emphasis on predicting future impact, and at the time of this
writing, it is not yet available to the public [8]. Another artificial intelligence–enabled search engine with a business focus, AlphaSense, has been available by paid subscription since 2010 [9].

 

Semantic Scholar @ Medium

 

Fonte: https://medium.com/ai2-blog/conference-peer-review-with-the-semantic-scholar-api-24ab9fce2324

 

Uusing a topic model to compare a reviewer’s publication history with the text of a submitted paper, researchers are able to do well at finding qualified reviewers for a submitted paper.
An obstacle to putting this into practice, however, is obtaining that publication history to begin with. Secondly, there is the conflict-of-interest problem: reviewers should not be making judgments on papers by individuals with whom they have a personal or professional relationship.

 

For its 2020 conference, the Association for Computational Linguistics (ACL) partnered with Semantic Scholar to partially automate its peer review process [6]. They used Semantic Scholar data for conflict-of-interest detection and reviewer-match score calculation. Registrants were asked to locate themselves via a search on Semantic Scholar, and to note the Author ID assigned to them via the URL of the author page. This is a very lightweight process and can be done without creating an account on the website. However, creating an account allows an author to manually correct any errors that the automated models may have made, and enables a range of useful features such as automated research feeds and new research alerts.

 

Fonte: https://medium.com/ai2-blog/investing-in-semantic-scholars-knowledge-graph-23f0f9f341e6

We believe it will be a useful resource for many looking for an alternate source of data provided through the MAG and we intend to continue to invest in making it a more comprehensive, trustworthy, and authoritative resource for open science in the years to come.

 

Fonte: https://medium.com/ai2-blog/introducing-tldrs-on-semantic-scholar-f8310c51c1fb

 

TLDRs (Too Long; Didn’t Read) are super-short summaries of the main objective and results of a scientific paper, generated using expert background knowledge and the latest GPT-3 style NLP techniques. This new feature is now available in beta for nearly 10 million computer science papers and counting in Semantic Scholar.

The new TLDR feature in Semantic Scholar puts single-sentence, automatically-generated paper summaries right on the search results and author pages, allowing you to quickly locate the right papers and spend your time reading what matters to you.

A TLDR is typically composed of salient information (indicated by colored spans) found in the abstract, intro, and conclusion sections of a paper.

Fonte: https://medium.com/ai2-blog/semantic-scholars-partnership-with-non-profit-publisher-bioone-98220c8ae9da

 

Semantic Scholar is pleased to announce their newest partnership with BioOne, a non-profit publisher of more than 200 subscribed and open-access titles in the biological, ecological, and environmental sciences.

 

Fonte:  https://medium.com/ai2-blog/springer-nature-and-allen-institute-for-artificial-intelligence-ai2-expand-collaboration-to-1b6b54f96e6d

 

Scholars, we are excited to announce the news about expanded access to Springer Nature content, now available on Semantic Scholar. One of the leading scientific publishers has provided you with greater access to over 3 million additional papers to enhance your exploration, improve discovery, and help you find relevant content more efficiently.

Fonte: https://medium.com/ai2-blog/citation-intent-classification-bd2bd47559de

Last year we started a project to classify citations by their intent in an effort to make it easier for our users to understand why a specific author cited another paper.