Computational Lexicology is the use of computers in the study of the lexicon. It has been more narrowly described by others (Amsler, 1980) as the use of computers in the study of machine-readable dictionaries. It is distinguished from Computational Lexicography, which more properly would be the use of computers in the construction of dictionaries, though some researchers have used Computational Lexicography as synonymous with Computational Lexicology.
In any case, it was the appearance of machine-readable dictionaries (MRDs) that gave Computational Lexicology its start as a separate discipline within Computational Linguistics. The first widely distributed MRDs were the Merriam-Webster Seventh Collegiate (W7) and the Merriam-Webster New Pocket Dictionary (MPD). Both were produced by a government-funded project at Systems Development Corporation under the direction of John Olney. They were manually keyboarded as no typesetting tapes of either book were available. Originally each was distributed on multiple reels of magnetic tape as card images with each separate word of each definition on a separate punch card with numerous special codes indicating the details of its usage in the printed dictionary. Olney outlined a grand plan for the analysis of the definitions in the dictionary, but his project expired before the anslysis could be carried out. Robert Amsler at the University of Texas at Austin resumed the analysis and completed a taxonomic description of the Pocket Dictionary under NSF funding, however his project expired before the taxonomic data could be distributed. Roy Byrd et al. at IBM Yorktown Heights resumed analysis of the Webster's Seventh Collegiate following Amsler's work. Finally, in the 1980s at Bellcore, George Miller and Christiene Fellbaum completed the creation and wide distribution of a dictionary's in the WordNet project, which today stands as among the most widely distributed computational lexicology resource.
Computational lexicology has contributed to our understanding of the content and limitations of print dictionaries for computational purposes. Basically, almost every portion of a print dictionary entry has been studied ranging from:
- what constitutes a headword, - used to generate spelling correction lists
- what variants and inflections the headword forms, - use to empirically understand morphology
- how the headword is delimited into syllables,
- how the headword is pronunced, - used in speech generation systems
- the parts of speech the headword takes on, - used for POS taggers
- any special subject or usage codes assigned to the headword, - used to identify text document subject matter
- the headword's definitions and their syntax, - used as an aid to disambiguation of word in context
- the etymology of the headword and its use to characterize vocabulary by languages of origin, - used to characterize text vocabulary as to its languages of origin
- the example sentences,
- the run-ons (additional words and multi-word expressions that are formed from the headword), and
- related words such as synonyms and antonyms.
Many computational linguists were disenchanted with print dictionaries as a resource for computational linguistics because they lacked sufficient syntactic and semantic information for computer programs. The work on computational lexicology quickly led to efforts in two additional directions.
Successors to Computational Lexicology
First, collaborative activities between computational linguists and lexicographers led to an understanding of the role that corpora played in creating dictionaries. Most computational lexicologists moved on to build large corpora to gather the basic data that lexicographers had used to create dictionaries. The ACL/DCI (Data Collection Initiative) and the LDC (Linguistic Data Consortium) went down this path. The advent of markup languages led to the creation of tagged corpora that could be more easily analyzed to create compuational linguistic systems. Part of speech tagging and semantic tagging of corpora were created in order to test and develop POS taggers and semantic disambiguation technology.
The second direction was toward the creation of Lexical Knowledge Bases (LKBs). A Lexical Knowledge Base was deemed to be what a dictionary should be for computational linguistic purposes, especially for computational lexical semantic purposes. It was to have the same information as in a print dictionary, but totally explicated as to the meanings of the words and the appropriate links between senses. Many began creating the resources they wished dictionaries were, if they had been created for computational anaylsis purposes. Ontologies can be considered to be one interpretation of this goal, for artificial intelligence systems. WORDNET can be considered to be such a development, as can the newer efforts at describing syntactic and semantic information such as the FRAMENET work of Fillmore. Outside of computational linguistics, the Ontology work of artificial intelligence can be seen as an evolutionary effort to build a lexical knowledge base for AI applications that have to deal with language.