Acronym Disambiguation: A Domain Independent Approach
This addresses the issue of ambiguous acronyms in text processing for users in NLP and information retrieval, but it is incremental as it builds on existing embedding techniques.
The paper tackled the problem of acronym disambiguation by proposing a domain-independent system that retrieves expansions from sources like Wikipedia and uses Doc2Vec embeddings to score contexts, achieving an accuracy of 90.9% on a dataset with 707 acronyms and 14,876 disambiguations.
Acronyms are omnipresent. They usually express information that is repetitive and well known. But acronyms can also be ambiguous because there can be multiple expansions for the same acronym. In this paper, we propose a general system for acronym disambiguation that can work on any acronym given some context information. We present methods for retrieving all the possible expansions of an acronym from Wikipedia and AcronymsFinder.com. We propose to use these expansions to collect all possible contexts in which these acronyms are used and then score them using a paragraph embedding technique called Doc2Vec. This method collectively led to achieving an accuracy of 90.9% in selecting the correct expansion for given acronym, on a dataset we scraped from Wikipedia with 707 distinct acronyms and 14,876 disambiguations.