RE: Artificial Intelligence and Document Services

Thank you. I am glad that you also like the topic of document services. Indeed, we could use another vote of support to create the new group. Presently, we have 3 out of the total of 5 needed to launch the group.

Also, onto some artificial intelligence and knowledge representation topics, I’m exploring some interesting topics pertaining to new knowledge representation formats and new logic programming languages. I’m simultaneously considering Prolog, Swish (http://www.ninebynine.org/RDFNotes/Swish/Intro.html), C#, Java, JavaScript, and JavaScript decorators (https://github.com/tc39/proposal-decorators). I’m thinking about strongly-typed knowledge representation formats and logic programming languages with set-theoretical type semantics, first-class sets and classes, first-class variables, and language features including reflection, extensible metadata, and decorators.


Best regards,
Adam

From: Paola Di Maio<mailto:paola.dimaio@gmail.com>
Sent: Friday, February 5, 2021 7:37 PM
To: Adam Sobieski<mailto:adamsobieski@hotmail.com>
Cc: public-aikr@w3.org<mailto:public-aikr@w3.org>
Subject: Re: Artificial Intelligence and Document Services

Adam
I too think there is need for such work, although stil a long shot :-)
I wanted tos support you CG but cannot login, dont have time to figure it out now
hope clothes will support and lets synch up when you do
if not shout again and will figure out my password
P

On Wed, Feb 3, 2021 at 2:53 AM Adam Sobieski <adamsobieski@hotmail.com<mailto:adamsobieski@hotmail.com>> wrote:
W3C Artificial Intelligence Knowledge Representation Community Group,

Exciting news: a new Community Group is proposed here: https://www.w3.org/community/ , the Document Services community group. Please feel free to login to the W3C community page and to support creation of the new group.

Also, some discussion is underway here: https://github.com/WICG/proposals/issues/19 . Please feel free to join the discussion.

The gist is to develop and standardize an architecture for document services, remote or client-local services on documents, document elements, or ranges of content. Examples of document services include: spellchecking, grammar checking, proofreading, fact checking, mathematical proof checking, reasoning checking, and argumentation checking. Imagine being able to check, in real-time, if a document has any informational, warning, or error messages with respect to its factuality or any steps of its reasoning. Tools for authoring and reviewing documents, in these regards, would be useful across sectors, across industry, academia, military, and government, with specific applicability to journalism, encyclopedias, digital textbooks, and science.

Three broad varieties of document services are, thus far, considered. Firstly, there are services which adhere to an informational message, warning, error pattern. Secondly, there are services which offer corrections, recommendations, or options for users. Thirdly, there are services which provide metadata about documents, document elements, or ranges of content (e.g. word count, reading level).

Here are a few hyperlinks which highlight the intersection of AI and document services.

With respect to fact checking:
https://www.logically.ai/
https://fullfact.org/
https://adverifai.com/

Here is a hyperlink pertaining to the intersection of AI and narrative checking:
https://authors.ai/

Many AI technologies will be facilitated by new architecture for document services in Web browsers. We hope to facilitate these technologies in the proposed Document Services community group: https://www.w3.org/community/ .


Best regards,
Adam Sobieski