Computer Lexicons

Voice Browser Working Group,

Greetings.  Computer lexicons are a component to many natural language systems.  The pronunciation lexicon specification (http://www.w3.org/TR/pronunciation-lexicon/) is used by both automatic speech recognition and speech synthesis engines in voice browser applications. Computer lexicons are also utilized in some approaches to machine translation.

Some existing computer lexicon formats include: EPUB3 (http://idpf.org/charters/2012/dictionaries/ http://code.google.com/p/epub-revision/wiki/DictionariesGlossaries), TEI (http://www.tei-c.org), OLIF (http://www.olif.net/), Apple Dictionary Services Markup (http://developer.apple.com/library/mac/#documentation/UserExperience/Conceptual/DictionaryServicesProgGuide/schema/schema.html#//apple_ref/doc/uid/TP40006152-CH4-SW1), and WordNet (http://wordnet.princeton.edu/).

With approaches for parallel markup, such as those in MathML3 (http://www.w3.org/TR/MathML3/chapter5.html), portions of lexicon entries, including for machine-utilizable semantic definitions, could make use of multiple formats such as both text and RDF.

Additionally, integrated development environments can be of use for creating and updating computer lexicon data.  Grammatical Framework (http://www.grammaticalframework.org/), for example, illustrates a programming language approach to grammatical data, and it is possible that such approaches can be of use to computer lexicon design and development processes.

Informationally, CogAlex-III, a SIGLEX endorsed, post-COLING workshop (http://pageperso.lif.univ-mrs.fr/~michael.zock/cogalex-3.html), indicative of contemporary lexicography, is upcoming and will be discussing the analysis of the conceptual input of dictionary users, the meaning of words, structure of lexicons, methods for crafting dictionaries or indexes, dictionary access (navigation and search strategies), and interface issues, in December.



Kind regards,

Adam Sobieski