@inproceedings{koehn-senellart-2010-fast,
title = "Fast Approximate String Matching with Suffix Arrays and A* Parsing",
author = "Koehn, Philipp and
Senellart, Jean",
booktitle = "Proceedings of the 9th Conference of the Association for Machine Translation in the Americas: Research Papers",
month = oct # " 31-" # nov # " 4",
year = "2010",
address = "Denver, Colorado, USA",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2010.amta-papers.2",
abstract = "We present a novel exact solution to the approximate string matching problem in the context of translation memories, where a text segment has to be matched against a large corpus, while allowing for errors. We use suffix arrays to detect exact n-gram matches, A* search heuristics to discard matches and A* parsing to validate candidate segments. The method outperforms the canonical baseline by a factor of 100, with average lookup times of 4.3{--}247ms for a segment in a realistic scenario.",
}
Markdown (Informal)
[Fast Approximate String Matching with Suffix Arrays and A* Parsing](https://aclanthology.org/2010.amta-papers.2) (Koehn & Senellart, AMTA 2010)
ACL