---
title: "Building a Phonics Engine for Automated Text Guidance"
author: "Dominik Lukeš (Dyslexia Action), Chris Litsas (NTUA)"
outline_version: 2
auto_title_slide: false
auto_thanks_slide: false
---

## Building a Phonics Engine for Automated Text Guidance
{id=pptx-21f9f991759d-001} {title}

![The iLearnRW project logo: the word “ilearn” in blue with “RW” in red above a curved line of stars.](assets/media/img-baeb0f72001b5327.png)

Dominik Lukeš

Dyslexia Action

Chris Litsas

NTUA

www.ilearnrw.eu

## Outline
{id=pptx-21f9f991759d-002}

- Struggling readers needs
- Linguistic background
- Phonics engine need
- Phonics engine specification
- Phonics engine implementation
- Phonics engine applications
- Next steps

## Needs of dyslexic people
{id=pptx-21f9f991759d-003}

- 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

## Linguistic background
{id=pptx-21f9f991759d-004}

> 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)

## Linguistic background
{id=pptx-21f9f991759d-005}

- t**ough**, th**ough**, thr**ough**, b**ough**, th**ough**t, c**ough**, hicc**ough**
- hosp.i.tal vs. hos.pit.al
- kitt.en vs. kit.ten
- walked, stopped, faked, tried
- exgirlfriend vs. exigent vs. exit
- English vs. Greek

## Phonics engine need
{id=pptx-21f9f991759d-006}

- 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

## Phonics engine specification
{id=pptx-21f9f991759d-007}

- 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

## Phonics engine implementation
{id=pptx-21f9f991759d-008}

- Profile of phonic difficulties
- Annotated phonic dictionary
- Look up routines

## Phonics profile - categories
{id=pptx-21f9f991759d-009}

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)

## Phonics profile (JSON)
{id=pptx-21f9f991759d-010}

{"descriptions":["a-æ"],

"problemType":"LETTER_EQUALS_PHONEME",

"humanReadableDescription":"a=æ (at) <> Pronounce a as æ. For example: at, as, and",

"cluster":3,

"character":"Short vowel"}

## Phonic dictionary
{id=pptx-21f9f991759d-011}

| | |
|---|---|
| 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 |

## Building the phonic dictionary
{id=pptx-21f9f991759d-012}

- 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)

## Phonics engine applications
{id=pptx-21f9f991759d-013}

- 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

## Phonics aware reader
{id=pptx-21f9f991759d-014}

![A word information card for “insects” showing its stem, its syllables “in-sects”, its sounds, and details of its suffix, syllables and vowels, with an OK button.](assets/media/img-3985805ec8ac000c.png)

## Phonics aware reader
{id=pptx-21f9f991759d-015}

![A Highlight Settings panel with a Text Rules list of vowel spellings such as a=æ (at) and e=e (get), each with an ON switch.](assets/media/img-97b9278f528e0bc6.png)

![Sample text in a large spaced typeface, “time. Fossils tell us that they were alive at the time of the mammoths.”, with some letters in lighter colours.](assets/media/img-bf2e8db6565e5f96.png)

## Game support
{id=pptx-21f9f991759d-016}

![A game screen in which the word “unless” is split into the coloured parts “un” and “less” above a scientist character, a clock and a percentage score.](assets/media/img-548612bce87e63a6.png)

## Online text tools
{id=pptx-21f9f991759d-017}

![A web tool with a profile menu showing “english_profile”, a box of pasted news text, and a Generic Metrics table: for example 186 words, 8 sentences and 5 paragraphs, with an average word length of 5.02 and a Flesch-Kincaid score of 12.76.](assets/media/img-93c71eab4c4cae1e.png)

## Online text tools
{id=pptx-21f9f991759d-018}

![A web tool showing counts of difficulties under Consonants, Vowels and Blends and Letter Patterns as numbered red circles, and a table of words such as financing, international, analysts, bank and and, with their syllables and phonetic spellings.](assets/media/img-4eb3ab1cf1392ddd.png)

## Online text tools
{id=pptx-21f9f991759d-019}

![An iLearnRW web page headed “english_profile, Difficulties List” listing vowel rules such as “iCe=aɪC (time)”, with an Active Rules panel showing the rule “a=æ (at)” and a Paint Problematic Word Parts menu.](assets/media/img-4631d1062cf28a2e.png)

## Online text tools
{id=pptx-21f9f991759d-020}

![Two paragraphs of news text about Greece and its creditors in which some letters a are shown in red.](assets/media/img-ecb9ff0580e7bc0e.png)

## Next steps
{id=pptx-21f9f991759d-021}

- 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

## www.ilearnrw.eu
{id=pptx-21f9f991759d-022}