Classifier-based acronym extraction for business documents

• Published in: Knowledge and information systems Vol. 29; no. 2; pp. 305 - 334
• Main Authors: MENARD, Pierre Andre, RATTE, Sylvie
• Format: Journal Article
• Language: English
• Published: London Springer-Verlag 01.11.2011; Springer; Springer Nature B.V
• Subjects: Acronyms; Algorithms; Applied sciences; Artificial intelligence; Automotive engineering; Business; Candidates; Classification; Computer Science; Computer science; control theory; systems; Data Mining and Knowledge Discovery; Data processing. List processing. Character string processing; Database Management; Dictionaries; Digital libraries; Exact sciences and technology; Extraction; Heuristic; Information Storage and Retrieval; Information systems; Information Systems and Communication Service; Information Systems Applications (incl.Internet); Information systems. Data bases; IT in Business; Mathematical analysis; Memory organisation. Data processing; Regular Paper; Sentences; Similarity; Software; Speech and sound recognition and synthesis. Linguistics; Studies; Similarity feature; Acronym extraction; Classification; Machine learning; Business document mining; Information extraction; Natural language processing; Text; Data mining; Business process; Language processing; Natural language; Acronym; Artificial intelligence; Sentence; Pattern extraction; Biomedical engineering
• ISSN: 0219-1377; 0219-3116
• DOI: 10.1007/s10115-010-0341-9

Acronym extraction for business documents has been neglected in favor of acronym extraction for biomedical documents. Although there are overlapping challenges, the semi-structured and non-predictive nature of business documents hinder the effectiveness of the extraction methods used on biomedical documents and fail to deliver the expected performance. A classifier-based extraction subsystem is presented as part of the wider project, Binocle, for the analysis of French business corpora. Explicit and implicit acronym presentation cases are identified using textual and syntactical hints. Among the 7 features extracted from each candidate instance, we introduce “similarity” features, which compare a candidate’s characteristics with average length-related values calculated from a generic acronym repository. Commonly used rules for evaluating the candidate (matching first letters, ordered instances, etc.) are scored and aggregated in a single composite feature that permits a supple classification. One hundred and thirty-eight French business documents from 14 public organizations were used for the training and evaluation corpora, yielding a recall of 90.9% at a precision level of 89.1% for a search space size of 3 sentences.