User:CarlMati/sandbox

In 1986 Carl Mattocks founded Tome Associates in London England which created the prize winning software that was recognized as the world's first AI search agent "TOME Searcher". Other Tome founders were the well respected Information Scientists Alina Vickery and her husband Professor Brian Vickery, from the University of London. Whom had developed some pioneering software with a small team of computer experts at UCL that used an expert system to formulate and then modify boolean search strategies (sets of words combined with AND, OR and NOT that you could use to search textual databases) from naively stated 'natural language' questions (i.e. ordinary English). That original research was funded by the British Library in 1983 to assess the potential for Expert Systems to replicate the skills of an 'Expert Intermediary' (librarian) to retrieve manageable volumes of relevant results from online databases. Mostly these databases were maintained by institutions such as the IEEE (electronics and computing) and the API (oil and gas). Although they did not have a 'search engine' they did  contain carefully indexed references and summaries of articles, books and published papers in the subjects they covered.

Although most of the world had no notion about what the AI (Artificial Intelligence) powered Searcher could do for them the Tome Associates team gained many supporters (see links below) Fortunately, the Marketing Director and myself became accomplished at that task, which was similar to that of trying to describe what a Generative AI powered Chatbot can do for people who have not used google, explored the digital world or even used the internet. Specifically he and I, together and separately, soon had interviews on the Canadian and  BBC news programs after a press conference at the Royal Institution in London. Over the five years Tome existed also spoke at numerous industry conferences and travelled the world giving presentations at The World Bank, United Nations, IBM, AT&T, Exxon, the British Home Office, European Space Agency, European Commission and countless other governmental and corporate institutions.

Often we were invited to expand on how the layers of the system semantics supported the Natural Language Conversations. We explained that to understand the words in the "Ask" the agent (aka chatbot) compared them to the data indexes / summaries and then engaged in a conversation about refining their "request"  using additional facets that may have been synonyms, broader terms, narrower more precise terms and /or related terms (as from multi-lingual thesaural-like structures utilized by an expert) in order to help the user succeed.

For example, if Tome Searcher was use as an AI Chatbot it would likely have said to someone who asked about "Organic Gifts"  'I assume you may have an interest in gifts from florists, in which case here are the nearest to you that local people say are good, and some have a special discount today. '

For a better sense of what Tome Searcher was capable of and what the technology offered beyond please peruse the following publications. note: Most of them discuss the merits of having an intelligent query assistant, which formulates an IR [ http://www.soi.city.ac.uk/~ser/papers/JDocHistory.pdf ] search strategy from natural language and is oriented for searching specific (discipline / domain / national language) information e.g. animal and plant welfare http://www.unu.edu/unupress/unupbooks/uu07ee/uu07ee0h.htm

http://www.nal.usda.gov/awic/newsletters/v2n1.htm.

Leader of IMIS a pan-european institute project developing an intelligent multilingual interface to english/ french/ german/ spanish online data sources.

http://is.uni-sb.de/vibi/ibmag/gensshei.html