Acronym Extraction System and Method of Identifying Acronyms and Extracting Corresponding Expansions from Text

Abstract

An acronym expansion system of the present invention receives electronic documents and extracts acronyms and their corresponding expansions. A part-of-speech tagger decomposes text into string tokens or words and tags them with their part-of-speech, while an acronym identifier determines whether a word is a potential acronym based on various conditions. An expansion identifier retrieves lists of words preceding and following a potential acronym to search for the expansion. The resulting word lists are examined sequentially to identify and retrieve an expansion for the potential acronym. An expansion extractor receives the potential acronym and a processed word list to retrieve the expansion of the potential acronym from that list. The extractor may utilize information from prior search iterations, and verifies an extracted expansion against a set of rules to remove spurious expansions.

Description

BACKGROUND OF THE INVENTION [0001] 1. Technical Field [0002] The present invention pertains to text analysis and processing systems. In particular, the present invention pertains to a system that identifies acronyms and extracts the appropriate acronym expansion from text. [0003] 2. Discussion of Related Art [0004] An acronym is a word that is formed from the initial letter or letters of each component of a compound term (e.g., NATO, RADAR, SNAFU, etc.), while an abbreviation is a shortened form of a written word or phrase that is used or substituted for the whole word (e.g., “amt” is an abbreviation for amount). Acronyms and abbreviations tend to overlap and are frequently used in daily verbal discourse, in written documents and in electronic documents and web pages on the Internet. In certain communities (e.g., military, engineering, medicine, etc.), numerous acronyms are employed constantly. For example, a page of a military document commonly includes in excess of ten acronyms. [...

AI Technical Summary

Benefits of technology

[0014] It is another object of the present invention to employ a bi-directional candidate search technique to select terms near an acronym in order to enhance identification of acronym expansions.

[0016] Still another object of the present invention is to apply rules to identified acronym expansions to verify the validity of those expansions and enhance accuracy.

Problems solved by technology

Acronyms may present challenges to readers in several manners.

In particular, individuals unfamiliar with a certain acronym tend to have difficulty understanding the acronym and using the acronym in vocabulary.

For example, commonly known acronyms, such as “LASER” and “CDROM”, are widely understood, while infrequently used or subject specific acronyms may be difficult for readers to understand (e.g., “AABFS” for Amphibious Assault Bulk Fuel System).

This process may be performed manually; however, preparing acronym lists with corresponding expansions in this fashion becomes prohibitive due to the effort required and is prone to errors.

In particular, the AcronymFinder system is highly inefficient due to the list being generated by manual submissions.

Further, the list is typically generic and static and may not suit or be tailored to various needs of particular organizations.

Although the above-described systems extract acronyms and corresponding expansions, the results produced by these systems have limited accuracy.

This tends to frustrate readers since the systems may omit acronyms within text or provide incorrect expansions for the acronyms, thereby requiring the reader to perform an additional task of ascertaining the correct expansion in another manner (e.g., manually).

Images