Abbreviation detection

Question

Under what field of study under natural language processing does abbreviation detection come? Looking for sources to learn abbreviation detection. I have considered Semantics, which basically detect synonyms. so i thought i might do multi-word semantics that would detect that "nlp" and "natural language processing" are similar. but i have found NO solution to do multi-word semantics.

Note: I know its really easy to down vote this question, but try to understand my problem. I have struggled for months now and any help is GREATLY appreciated...

Thankyou

Answer 1

(Automatic) Detection of abbreviations is also a major subproblem and task of sentence segmentation and tokenization processes in general, i.e.: disambiguate sentence endings from punctuation attached to abbrevations. Statistical methods (NLP) have been applied to detect and extract them successfully, mostly in a (semi-)supervised manner. E.g. the PUNKT system, which actually has been developed for sentence boundary detection, is able to detect abbreviations with high accuracy, based on the assumption that a large number of ambiguities in the determination of sentence boundaries can be eliminated once abbreviations have been identified (Kiss et al. 2006. Unsupervised Multilingual Sentence Boundary Detection).

Now, before trying to modify the PUNKT system or similar, I was just trying to give a direction wrt. NLP-based abbr. detection. The system mentioned above, for example, applies techniques to measure collocational strengths between pairs of tokens, which can be two words, but also a word and some punctuation, treated as a token. It's all based on frequencies and probabilites, although the results in traditional collocational analysis' do allow for semantic research.

Answer 2

Thankyou to all who helped me, I think i found an answer myself. I trust it because it is from a research paper by the person who invented the abbreviation expansion algorithm for Yahoo! and it also shows signs of artificial intelligence. Again, thankyou all.

To others in the same boat as me, here's the solution:

SEO by the sea - How search engines might expand abbreviations in search queries