Towards a single proposal in spelling correction

Abstract

The study presented here relies on the integrated use of different kinds of knowledge in order to improve first-guess accuracy in non-word context-sensitive correction for general unrestricted texts. State of the art spelling correction systems, e.g.ispell, apart from detecting spelling errors, also assist the user by offering a set of candidate corrections that are close to the misspelled word. Based on the correction proposals of ispell, we built several guessers, which were combined in different ways. Firstly, we evaluated all possibilities and selected the best ones in a corpus with artificially generated typing errors. Secondly, the best combinations were tested on texts with genuine spelling errors. The results for the latter suggest that we can expect automatic non-word correction for all the errors in a free running text with 80% precision and a single proposal 98% of the times (1.02 proposals on average).

Managing misspelled queries in IR applications

“…Given that applications of this kind in IR should require fully automatic correction (Agirre et al, 1998;Kukich, 1992), these methods can be extended to eliminate, as far as possible, any intermediate decision to be made by the user. One of the first attempts in this sense was to consider phonetic information when applying correction, assuming that misspellings arise because the user types a query that sounds like the target term (Bourne and Ford, 1961).…”

“…However, in IR systems, this kind of interaction is impractical. Therefore, the strategies considered for IR systems should assure fully automatic treatment (Agirre et al, 1998;Kukich, 1992), with no need for the user to intervene after inputting the initial query.…”

Effect of OCR error correction on Arabic retrieval

“…Using grammar: in this approach, a passage containing spelling errors is parsed based on a language specific grammar. In a system described by Agirre, an English grammar was used to parse sentences with spelling mistakes (Agirre et al 1998). Parsing such Inf Retrieval (2008) 11:405-425 411 sentences gives clues to the expected part of speech of the word that should replace the misspelled word.…”

Robust Spelling Correction

“…Here, the state of the art [2] focuses on contextual and non-contextual error correction. In relation to the former, most proposals are based on nlp techniques and/or statistical-language models, integrating linguistic knowledge [3,4]. For the latter, techniques look for possible editing sequences to reflect the error occurrence phenomenon in spelling.…”