- From: Adeel <aahmad1811@gmail.com>
- Date: Mon, 23 Jan 2023 10:38:40 +0000
- To: Dan Brickley <danbri@danbri.org>
- Cc: Adam Sobieski <adamsobieski@hotmail.com>, ProjectParadigm-ICT-Program <metadataportals@yahoo.com>, "public-aikr@w3.org" <public-aikr@w3.org>, "semantic-web@w3.org" <semantic-web@w3.org>
- Message-ID: <CALpEXW3qFENZRFSL9P3xSYnqhWiNbmcMrK--OZFkaEmjPkBMkQ@mail.gmail.com>
legal speculation...? I work in the NLP space. I am relating to the topic of chatgpt? Your point was pointless. On Mon, 23 Jan 2023 at 10:37, Dan Brickley <danbri@danbri.org> wrote: > Periodic reminder: this list is not for legal speculation > > Thanks! > > On Mon, 23 Jan 2023 at 10:26, Adeel <aahmad1811@gmail.com> wrote: > >> Hello, >> >> All the embedding models are non-compliant to use in EU/UK region as they >> lack transparency. You can't really use them in regulated environments >> without loss of lineage in the data governance which is necessary for >> regulatory compliance. They probably need to prioritize interpretability >> and explainability within their models. But, likely they don't care because >> platforms like hugging face are based in USA where such trustworthy efforts >> are non-existent and not a priority. >> >> 1) how the result was produced >> 2) whether the model was correct in producing such a result based on the >> implementation >> 3) training dataset bias - bias debasing, etc. >> 4) how to resolve the bias laundering effect >> >> Thanks, >> >> Adeel >> >> >> On Sat, 21 Jan 2023 at 15:09, ProjectParadigm-ICT-Program < >> metadataportals@yahoo.com> wrote: >> >>> Large language model interfaces with knowledge bases are a key >>> ingredient for digital empowerment of all stakeholders in the promotion of >>> sustainable development. >>> >>> The sad reality is that of the 7,151 living languages (source: >>> http://www.ethnologue.com) fewer than 200 are served currently in NLP >>> applications and AI chatbots. >>> >>> Even though there are linguistic tools available in principle to support >>> digital environments for all languages with populations of speakers of e.g. >>> 1,000 or more the situation is comparable to the pharmaceutical industry >>> where only the discovery and development of new drugs for large enough >>> markets is pursued. >>> >>> So we can actually state that wide scale applications of chatbot >>> applications and similar AI NLP application will only widen the digital >>> divide. See more about this on https://www.sil.org. >>> <http://www.sil.org.> >>> >>> The GLIKI project (https://gliki.wordpress.com) was formulated to help >>> bridge this divide. This project is soon going into execution mode. >>> >>> It is also instructive to see what the IFLA, International Federation of >>> Library Associations (https://www.ifla.org) is doing in terms of open >>> access to knowledge. >>> >>> Open access to digital libraries and knowledge repositories is crucial >>> in developing countries and is currently a totally neglected and ignored >>> subject with Big Internet Tech companies, yet these developing countries >>> provide a huge potential customer base for internet services, in particular >>> for online education, online healthcare, cloud and edge computing services. >>> >>> Bilingual access (one international language and a native language) >>> could boost internet services and stimulate local development of NLP and AI >>> applications. >>> >>> Milton Ponson >>> GSM: +297 747 8280 >>> PO Box 1154, Oranjestad >>> Aruba, Dutch Caribbean >>> Project Paradigm: Bringing the ICT tools for sustainable development to >>> all stakeholders worldwide through collaborative research on applied >>> mathematics, advanced modeling, software and standards development >>> >>> >>> On Friday, January 20, 2023 at 12:39:15 AM AST, Adam Sobieski < >>> adamsobieski@hotmail.com> wrote: >>> >>> >>> Hello. I am also thinking about artificial neural networks, dialogue >>> systems, and Semantic Web technologies, as Xavier asked about. I agree with >>> Paola that natural-language interfaces to knowledgebases have been a while >>> coming. Thank you, Dan, for pointing out: >>> https://github.com/jerryjliu/gpt_index . >>> >>> In the near future, it could be the case that content could move between >>> the semantic working memories of artificial neural networks and external >>> knowledgebases. >>> >>> I would like to share a hyperlink to an article which I recently wrote. >>> The article discusses artificial neural networks, (cognitive) semantics, >>> and semantic cognition. The article is, however, more about DALL-E 2 than >>> ChatGPT. >>> >>> In the short article: I envision systems which can bidirectionally >>> transform content pairwise between language, visual imagery, and semantics; >>> I discuss the ideas of artificial concepts, categories, attributes, and >>> relationships; and I show that varieties of multimodal semantics are >>> already enhancing the performance of AI systems with respect to visual >>> question answering, language-related, and vision-related tasks. >>> >>> The article is available here: >>> https://www.linkedin.com/pulse/artificial-neural-networks-semantic-cognition-adam-sobieski/ >>> . >>> >>> If you enjoy the article, please do like and share it on LinkedIn! Thank >>> you. >>> >>> >>> Best regards, >>> Adam >>> >>> ------------------------------ >>> *From:* Dan Brickley <danbri@danbri.org> >>> *Sent:* Thursday, January 19, 2023 12:56 AM >>> *To:* Paola Di Maio <paoladimaio10@gmail.com> >>> *Cc:* SW-forum <semantic-web@w3.org>; W3C AIKR CG <public-aikr@w3.org> >>> *Subject:* Re: ChatGPT, ontologies and SPARQL >>> >>> >>> >>> On Thu, 19 Jan 2023 at 04:14, Paola Di Maio <paoladimaio10@gmail.com> >>> wrote: >>> >>> The semantic web has been waiting for natural language interfaces (well, >>> at least I have) >>> for decades, ideally read and write >>> if this tool can be used like that then lets see it >>> >>> @Danbri share results sometime? >>> >>> >>> Search twitter: chatgpt sparql >>> … lots of folk experimenting >>> >>> Dan >>> >>> >>> >>> >>> On Wed, Jan 18, 2023 at 10:33 PM Dan Brickley <danbri@danbri.org> wrote: >>> >>> >>> >>> On Wed, 18 Jan 2023 at 14:21, Paola Di Maio <paola.dimaio@gmail.com> >>> wrote: >>> >>> fyi - would be good to be able to generate sparql queries and interact >>> with ontologies using natural language >>> thanks to this user for discovering this feature >>> >>> >>> In general these new large LLM models seem to have a weird effect on >>> commentators: their ability to casually and confidently just make up >>> answers, tends to distract from their less exciting but potentially >>> transformative ability to kinda-sorta-kinda “understand” questions >>> expressed in natural language. >>> >>> Dan >>> >>> ps. folk here might find >>> https://github.com/jerryjliu/gpt_index worth exploring, as a tool that >>> supports idea of combining LLMs with external data. I have also had >>> promising results using GPT-* etc to generate SPARQL… >>> >>> >>> >>> ---------- Forwarded message --------- >>> From: *Paola Di Maio* <paola.dimaio@gmail.com> >>> Date: Wed, Jan 18, 2023 at 10:15 PM >>> Subject: Re: ChatGPT, ontologies and SPARQL >>> To: Contact - Cogsonomy <contact@cogsonomy.fr> >>> Cc: Semantic Web <semantic-web@w3.org> >>> >>> >>> assuming the syntax is good >>> (your example validates here http://sparql.org/$/validate/query) >>> then it looks like a big YES >>> It would be amazing to have a tool that can translate natural language >>> queries into sparql >>> and remove a major hurdle to using open ontologies on the web >>> Please, lets set up a catalogue of examples and evaluate the results >>> great functionality if it works >>> thank you >>> >>> >>> On Tue, Jan 17, 2023 at 10:41 PM Contact - Cogsonomy < >>> contact@cogsonomy.fr> wrote: >>> >>> Hi, >>> >>> I asked chatGPT to create a sparql query for DBPedia by translating my >>> question expressed in natural language : "Give me all the names of the >>> cities located in France whose number of inhabitants is greater than >>> 10,000". >>> >>> Its answer was as follows : >>> >>> *here's the SPARQL query to answer the question:* >>> >>> *PREFIX dbo: <http://dbpedia.org/ontology/> >>> <http://dbpedia.org/ontology/>* >>> *PREFIX dbr: <http://dbpedia.org/resource/> >>> <http://dbpedia.org/resource/>* >>> *SELECT ?city * >>> *WHERE {* >>> * ?city a dbo:City;* >>> * dbo:populationTotal ?population;* >>> * dbo:country dbr:France.* >>> * FILTER (?population > 10000)* >>> *}* >>> >>> *This query uses the dbo prefix to access the DBpedia ontology and the >>> dbr prefix to access the DBpedia resources. It selects the names of cities >>> (?city) that are instances of dbo:City, have a total population >>> (?population) greater than 10000, and have the dbo:country property with >>> the value dbr:France (which represents France).* >>> >>> We can see on social networks several tests of chatGPT related to >>> ontologies. Do you think we can use chatGPT to query natural language >>> ontologies (if we give it the structure before, of course)? And if we give >>> a consequent corpus in learning to the GPT-3 algorithm (or its successor), >>> do you think that it could build the ontology based on this corpus? More >>> generally, will our vision of ontologies not be modified by the arrival and >>> the rise of this kind of tool? >>> >>> Best regards, >>> >>> Xavier >>> >>>
Received on Monday, 23 January 2023 10:39:10 UTC