Word Prediction: What's Good Enough
So, you’ve concluded that word prediction is an effective way to bridge the gap between thoughts and written expression. Now, how do you decide on a word prediction program? What are the distinguishing differences in word prediction programs? And, what is good prediction worth?
Would you ever compromise the quality of medical attention you seek for your family? Would you buy a car that tested “poor” in consumer safety reports? Reading and writing skills are just as critical and we need to consider them as such. People with learning difficulties or writing challenges sometimes only have brief moments of opportunity — when those moments come, we must be there with the best tools to make sure that they have a successful experience. We must look at word prediction with the same critical eyes if we are to offer the best possible opportunity for success.
We often receive questions from educators, parents, and employers/employees regarding word prediction functionalities in Read&Write. These questions go into areas like grammar, subject-specific vocabulary, phonetic spelling suggestions, and the various prediction modes available. We understand there can be confusion about the functionalities offered by the different assistive technology tools out there.
Now you might be wondering, how does Read&Write stack up in terms of word prediction capabilities? What makes it stand out? Most importantly, is the word prediction feature within Read&Write "good enough" for creating an inclusive environment - whether that’s in the classroom or the workplace.
We believe everyone deserves the opportunity to understand and be understood. We understand there can be confusion about the functionalities offered by the different word prediction tools out there.
By choosing Read&Write, you gain access to Co:Writer prediction, a powerful tool that empowers learners and employees of all abilities to:
- Express themselves more effectively: Co:Writer prediction's accurate word suggestions help users find the right words to convey their ideas clearly.
- Improve fluency and writing speed: Getting word suggestions while writing helps users to maintain writing flow. This means they can focus on the content rather than getting stuck on spelling.
- Expand vocabulary: Co:Writer prediction personalizes suggestions based on subject style, helping users discover new words within the context of their work or studies.
Co-Writer prediction is just one of the many features in Read&Write that empowers students and employees of all abilities to reach their full potential.
History of Co:Writer Prediction
Co:Writer® was produced and is continually updated in collaboration with Paul Schwejda and Judy McDonald, who are true pioneers and have been perfecting word prediction for over 30 years. They began their investigation into word prediction back in the late 70’s. In the early 80’s they produced “Predict It.” but memory on those old Apple II computers caused some limitations. When the Macintosh came to market, Co:Writer was born.
Macintosh presented the opportunity to develop word prediction with many enhanced features. Co:Writer was released as a stand alone product by Don Johnston Inc in 1992, and as technological advances have continued to be made, they have remained singularly devoted to the innovation, refinement, and perfection of Co:Writer’s prediction and its ability to support struggling writers. In July 2024, we adopted Co:Writer as the word prediction tool of choice in Read&Write because it is the strongest, and most accurate word prediction available on the market.
History of Word Prediction
Word Completion
This type of prediction is useful when filling out forms. If you begin to type, for example, the date “j-a-n-u,” the application predicts January xx, xxxx (the current date).
Bigram/Trigram Prediction (patterns)
This type of prediction uses two and three-word patterns, and the frequency in which those two or three words appear together. There are three key issues with regard to this type of word prediction:
- The effectiveness of the pattern prediction hinges completely on the types of text the developers have used to analyze word patterns in general. Developers have used such common mediums as newspapers. Vocabulary and word patterns found in newspapers do not support the needs of a beginning writer.
- This prediction is not effective when new words or topic words are entered because pattern prediction is dependent on the word patterns established by analyzing other writing. This type of prediction only becomes effective after repeated use. The impact on the student is that correct predictions do not occur efficiently because the software needs to monitor the word usage to establish proper prediction. For a struggling writer, if the word is not predicted properly it will not be used as frequently.
- New words entered need to contain all forms of the word to be predicted correctly because prediction is not based on grammar and root words. This requires you to enter every form of any given word. For example, if the word explore was not in the dictionary, the word would need to be entered multiple times: explore, explores, explored, exploring, explorer for prediction to occur for all forms of the word. Consequently, a struggling writer would only be presented with that form of the word that was entered.
Linguistic Word Prediction
One of the building blocks at the foundation of Co:Writer’s prediction engine is called “Linguistic Word Prediction.” With Linguistic Word Prediction, Co:Writer knows the grammatical value of each word in its dictionaries. When Co:Writer learns new words collected from articles or an individual’s writing, it automatically assigns grammar to them. With grammar-based intelligence, Co:Writer can accurately predict words within the framework of valid sentence structures. It also gives flexibility to the words it learns by automatically predicting in multiple tenses and usages.
Natural Language Processing
The foundation of Natural Language Processing (NLP) stems back to the 1950s, but it wasn’t until recently that machine learning was combined with large-scale real-world writing and human-to-machine interactions. This technology is at the foundation of automated assistants including Siri, Amazon’s Alexa, and Google Assistant.
This technology continues to progress rapidly and while it’s not yet at the level where there is no distinction between machine and human, that gap is narrowing every year. NLP allows the word prediction engine to identify trigger words and phrases to better understand context so it can better predict appropriate words based on that topic.
Neuron™ Word Prediction
Co:Writer’s Neuron™ prediction engine follows the natural relationships of ideas and concepts in the brain. Co:Writer’s core word prediction engine is based on several core technologies—Natural Language Processing, Linguistic Word Prediction, Phonetic / Flexible Spelling, and Topic Dictionaries. The best of these technologies are combined using sophisticated algorithms based on real-world writing and trillions of testing scenarios. The result is an elegantly simple-to-use word prediction engine specifically designed to free up ideas so they more naturally flow into writing—helping overcome writer’s block, word recall.
Additional Word Prediction Components
Topics
Topics are a functionality exclusive to Read&Write where lists of words are grouped together by content areas that can be activated or deactivated manually when writing on topics containing complex topic-specific words. Rather than struggling over how to spell Pterodactyl or Tyrannosaurus, students can focus on writing for meaning and retelling their knowledge. Rather than struggling to spell technical terms like 'Photosynthesis' or 'Thermodynamics,' employees can focus on writing reports and conveying their ideas clearly.
Applying a Topic dictionary increases users’ efficiency by getting to content-specific words in just one or two keystrokes. There are over 500 Topic dictionaries built into Co:Writer.
Phonetic Spelling
Co:Writer prediction provides every conceivable letter-pattern users will try in an attempt to spell out words. A great deal of research and assessment has been done to provide scaffolding for writers who might struggle more severely.
Student-safe
In addition, care was taken to make Co:Writer’s predictions appropriate for students. Unlike many other prediction tools which are often lewd because they’re based on searches from the general population, Co:Writer prediction has built-in filters to screen out insensitive and inappropriate words.
In the end, it's going to be your call — what is good enough?
Ultimately, choosing the right word prediction tool is about making sure individuals can express their thoughts clearly and efficiently. Co:Writer prediction in Read&Write stands out with advanced features and user-focused design, making it the perfect solution for both education and work. By prioritizing quality and inclusivity, we ensure that everyone has the opportunity to reach their full potential.