Jennifer Pedler's research while affiliated with Birkbeck, University of London and other places
What is this page?
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
Publications (5)
One of the methods that has been proposed for dealing with real-word errors (errors that occur when a correctly spelled word is substituted for the one intended) is the "confusion-set" approach - a confusion set being a small group of words that are likely to be confused with one another. Using a list of confusion sets drawn up in advance, a spellc...
Word-processors are widely used by dyslexics but the spellcheckers are often not appropriate to their needs. This paper examines a sample of around 3000 words of running text containing almost 600 errors typical of those made by dyslexics. It first describes the types of error and the ways in which they differ from the more conventional misspelling...
One of the methods that has been proposed for dealing with real-word errors (errors that occur when a correctly spelled word is substituted for the one intended) is the "confusion-set" approach - a confusion set being a small group of words that are likely to be confused with one another. Using a list of confusion sets drawn up in advance, a spellc...
Corpora of dyslexic texts are valuable for studying dyslexia and addressing accessibility practices, among others. However, due to the difficulty of finding texts written by dyslexics, these kind of resources are scarce. In this paper, we introduce a small Spanish corpus of dyslexic texts with annotated errors. Since these errors require non-standa...
Citations
... Even spelling correction programs may mistakenly generate a real-word error while attempting to adjust non-word errors, in cases where the "auto-correct" feature is enabled in the text processing setting (Hirst and Budanitsky, 2005;Dashti, 2017). Detailed investigation of real-word spelling corrections has been proposed by Pedler (2007) Hirst and Budanitsk (2005). Of course, Kukich (1992) has more extensively explored spelling correction. ...
... Few studies have focused on the compilation of corpora of texts written by people with dyslexia to annotate and analyze their errors in order to design specific tools. To the best of our knowledge, the literature on this specific subject is limited to the following studies: two studies in English (Pedler, 2007), two studies in Spanish (Rello et al., 2012(Rello et al., , 2014, one study in German (Rauschenberger et al., 2016) and one study in French (Antoine et al., 2019). ...
Reference: Spelling errors made by people with dyslexia
![[object Object]](https://i1.rgstatic.net/ii/profile.image/395977514078209-1471419804934_Q64/Ricardo-Baeza-Yates.jpg)
![[object Object]](https://i1.rgstatic.net/ii/profile.image/277200055095298-1443101051337_Q64/Horacio-Saggion.jpg)
... As we noticed, sequence generation for word2vec training does influence success rates, so we are currently exploring further ways of sequence generation. We would also like to introduce mild supervision element by generating more data for word2vec training by mutating dictionary words using confusion sets (Pedler and Mitton, 2010). We would also like to explore the effectiveness of our approach on languages other than English. ...
... Computer spell checkers turned out to be a very useful tool for writers and students. These checkers make them able to write texts containing lower error rates, but the case is not like this with students with dyslexia because conventional spell checkers will not be able to discover their spelling mistakes, so, these checkers suggest wrong or misleading corrections [9]. This made devising sophisticated algorithms and methods for automatic text correction a challenge that researchers face constantly. ...
... Character confusion sets were used before, predominantly in a Chinese language setting (Liu et al., 2013;Chen et al., 2013;Wang et al., 2018Wang et al., , 2019a. Word level confusion sets were studied as well, focusing on grammatical error correction (Wang et al., 2019b;Choe et al., 2019;Grundkiewicz et al., 2019), preposition usage (Rozovskaya and Roth, 2010), and dyslexic errors (Pedler and Mitton, 2010). ...
