I have removed inline external links, and have reduced the article size substantially. I suspect this is not enough to get this accepted, even as a "stub" article, as again: it is my pet subject. Should I be requesting for the article to be created instead? MartinWheatman (talk) 15:46, 14 October 2019 (UTC)
191003-pronoun / 3 October 2019
Search Enguage on Amazon.
Enguage is the open source natural language understanding program which won the BCS SGAI Machine Intelligence Competition in 2016. However, it is neither intelligent nor does it understand natural language. It is a program which arbitrarily maps, or translates, one natural number onto another. An utterance, an array of strings of letters, encodes to a singe very large value, similar to Gödel Numbering. So ["i", "need", "a", "coffee"] is a single value in an arbitrary base, in the same way [1, 0, 2, 4] might represent 1,024 in base 10. Therefore, the translation of numbers gives the impression of utterance interpretation, for example "hello" might translate to "hello to you too".
Further, each translation is determined through a list of internal utterances associated with each utterance, which is followed until reply ... is interpreted. Enguage produces an impression of understanding because of its interaction with contextual data. These internal utterances may interact with external processes over TCP/IP links, with an internal OODb, or with the number translation process itself. Each translation is self-generated, or autopoietic: it is constructed by a built-in repertoire of utterances.
Enguage is available as open source so that the experiments describe can be repeated. It recognises that interpretation is context dependent and attempts to find the most appropriate understanding through user interaction.
Loops in translations can be created by recursion, so Enguage might be Turing Complete
Enguage is approximately 30,000 lines of Java, and can be run as a CLI or used through an API within an application. The name Enguage is a portmanteau of engine and language.
Other articles of the topic Free and open-source software : Deeplearning4j, Minetest, TiMidity++, Sobi2, Jam.py (web framework), Conectiva, Xaraya
Some use of "" in your query was not closed by a matching "".Some use of "" in your query was not closed by a matching "".
- "Martin Wheatman". Retrieved 2019-10-08.
- "191003-pronoun". Retrieved 2019-10-08 – via GitHub.
- Wheatman, Martin. "Enguage development repository". GitHub. Unknown parameter
- "BCS Machine Intelligence Competition". Unknown parameter
- "BCS Machine Intelligence Competition Winners". Unknown parameter
- "Hello/Hello to you too". Unknown parameter
- Wheatman, M. J. (2014), Bramer, Max; Petridis, Miltos, eds., "An Autopoietic Repertoire", Research and Development in Intelligent Systems XXXI, Springer International Publishing, pp. 165–170, doi:10.1007/978-3-319-12069-0_11, ISBN 9783319120683, retrieved 2019-10-08
- Wheatman, Martin (2016), Baranauskas, Maria Cecilia Calani; Liu, Kecheng; Sun, Lily; Neris, Vânia Paula de Almeida, eds., "A Pragmatic Approach to Disambiguation in Text Understanding", Socially Aware Organisations and Technologies. Impact and Challenges, Springer International Publishing, 477, pp. 143–148, doi:10.1007/978-3-319-42102-5_16, ISBN 9783319421018, retrieved 2019-10-08
- Wheatman, Martin J. (2017). Bramer, Max; Petridis, Miltos, eds. "Programming Without Program or How to Program in Natural Language Utterances". Artificial Intelligence XXXIV. Lecture Notes in Computer Science. Springer International Publishing: 61–71. doi:10.1007/978-3-319-71078-5_5. ISBN 9783319710785.
This article "Enguage" is from Wikipedia. The list of its authors can be seen in its historical and/or the page Edithistory:Enguage. Articles copied from Draft Namespace on Wikipedia could be seen on the Draft Namespace of Wikipedia and not main one.