Building a phonics engine for automated text guidance
Download as PPTX, PDF1 like565 views
This document outlines the need for a phonics engine to provide automated guidance for struggling readers. It discusses the linguistic challenges dyslexic readers face and how a phonics engine could help by identifying phonetic patterns in words, appropriate syllable breaks, and word structure. The document then describes the specification, implementation, and applications of the phonics engine, including a phonics profile, annotated dictionary, and text highlighting tools to support readers and educational games. Next steps include expanding the dictionary and refining the lookup and highlighting routines.
![Phonics profile (JSON)
{"descriptions":["a-æ"],
"problemType":"LETTER_EQUALS_PHONEM
E",
"humanReadableDescription":"a=æ
(at) <> Pronounce a as æ. For
example: at, as, and",
"cluster":3,
"character":"Short vowel"}](https://image.slidesharecdn.com/buildingaphonicsengineforautomatedtextguidance-iisa-151009091348-lva1-app6892/85/Building-a-phonics-engine-for-automated-text-guidance-10-320.jpg)
Building a phonics engine for automated text guidance
- 1. Building a Phonics Engine for Automated Text Guidance Dominik Lukeš Dyslexia Action Chris Litsas NTUA www.ilearnrw.eu
- 2. Outline • Struggling readers needs • Linguistic background • Phonics engine need • Phonics engine specification • Phonics engine implementation • Phonics engine applications • Next steps
- 3. Needs of dyslexic people • Identifying the syllables in a word • Recognising the structure of words (stem, prefix, suffix) • Highlighting typical or repeated patterns of English orthography • Identifying phoneme/grapheme correspondence • Learning the pronunciation of a word • Learning the meaning of a word
- 4. Linguistic background Dearest creature in creation Studying English pronunciation, I will teach you in my verse Sounds like corpse, corps, horse and worse. Though the difference seems little, We say actual, but victual, Seat, sweat, chaste, caste, Leigh, eight, height, Put, nut, granite, and unite. Gerard Nolst Trenité - The Chaos (1922)
- 5. Linguistic background • tough, though, through, bough, thought, cough, hiccough • hosp.i.tal vs. hos.pit.al • kitt.en vs. kit.ten • walked, stopped, faked, tried • exgirlfriend vs. exigent vs. exit • English vs. Greek
- 6. Phonics engine need • Finding all examples of ‘a’ spelled to rhyme with ‘hay’ in a text or a corpus. • Sorting words by their phoneme/grapheme ratio. • Identifying appropriate syllable boundaries in the written form of a multi-syllable word based on knowledge of the syllable boundaries in pronunciation
- 7. Phonics engine specification • provide automated guidance to students and teachers reading texts (using highlighting as well as explicit information) • generate more extensive word lists for practice activities within the serious games • provide information about word structure to the game engine
- 8. Phonics engine implementation • Profile of phonic difficulties • Annotated phonic dictionary • Look up routines
- 9. Phonics profile - categories Based on a modified and expanded version of Dyslexia Action Literacy Programme • Consonants (49) • Vowels (71) • Blends and letter patterns (131) • Syllables (13) • Suffixes (92) • Prefixes (42) • Confusing letters (15)
- 10. Phonics profile (JSON) {"descriptions":["a-æ"], "problemType":"LETTER_EQUALS_PHONEM E", "humanReadableDescription":"a=æ (at) <> Pronounce a as æ. For example: at, as, and", "cluster":3, "character":"Short vowel"}
- 11. Phonic dictionary Word form: feelings Related stem: feeling Pronunciation: ˈfiː.lɪŋz Phoneme/Grapheme Mapping: f-f,ee-iː,l-l,i-ɪ,ng-ŋ,s-z Orthographic syllabification: fee.lings Number of letters: 8 Number of phonemes: 6 Number of syllables: 2 Frequency band: 4 Suffix type: SUFFIX_ADD Suffix form: s Prefix type: PREFIX_NONE Prefix form: NULL
- 12. Building the phonic dictionary • 5,000 most frequent words based on COCA • Generated derived forms by reversing hunspell • Used online tool to generate pronunciation • Create rules for matching pronunciation with spelling patterns • Create rules for displaying • Mark suffixes and prefixes and types • Adjust frequencies • Manual fine tuning (lots of regex)
- 13. Phonics engine applications • Phonics aware reader • Game support – generating word lists • Game support – provide word structure • Game support – link word structures to profile • Text classification tool • Online text annotation tool
- 16. Game support
- 21. Next steps • Bigger dictionary with more information on words • Finetuning of look up routines • More sophisticated highlighting routines • More sophisticated NLP – PoS – Sentence structure – Semantics • WordNet, Framenet • Named Entities • Collocations
- 22. www.ilearnrw.eu