Autocomplete using NLP

Proceedings of HCII, 2005

Mobile phone based SMS messaging is a ubiquitous form of communication in the modern world. However, the 12key keypad found on many mobile phones today poses problems for text entry. As three or four letters share the same key, some form of disambiguation is required to determine which letter is intended by the user. The predictive text entry method is the most common text entry technique used in present day mobile phones. To measure the efficiency of text entry, we perform a task analysis to model the actions of users and develop keystroke-level and time-level models. A corpus of SMS messages is collected and users were video-taped to obtain timing information for data analysis. Based on these models, we propose methods to improve the predictive text entry method, focusing on remapping letters to keys and examining predictive word completion. Using the time model, we show how both techniques can be reinforce each other to yield a reduction of over 25% of time for message input over the standard predictive text entry model. Please direct all correspondence to the second author, Min-Yen Kan.

Journal of Emerging Technologies and Innovative Research (JETIR), 2018

Researchers usually assess word prediction victimization keystroke savings, however, this live isn't easy. we have a tendency to gift many complications in computing keystroke savings which can have an effect on interpretation and comparison of results. we have a tendency to address this drawback by developing 2 gold standards as a frame for interpretation. These gold standards live the most keystroke savings under 2 totally different approximations of a perfect language model. The gold standards additionally slim the scope of deficiencies in a very word prediction system. Index Terms-word prediction, next word prediction, word generation ________________________________________________________________________________________________________ I. INTRODUCTION Word prediction is AN application of language modeling to rushing up text entry, particularly to coming into utterances to be spoken by AN Augmentative and different Communication (AAC) device. AAC devices look for to handle the twin drawback of speech and motor impairment by trying to optimize text input. Even still, communication rates with AAC devices square measure usually below ten words per minute (Newell et al., 1998), compared to the common 130-200 words per minute speech rate of speaking individuals. Word prediction addresses these problems by reducing the quantity of keystrokes needed to provide a message, that has been shown to boost communication rate (Trnka et al., 2007). The reduction in keystrokes conjointly interprets into a lower degree of fatigue from typewriting all day (Carlberger et al., 1997). Word prediction systems gift multiple completions of the present word to the user. Systems generate a listing of W predictions on the idea of the word being typewritten and a language model. The vocabulary is filtered to match the prefix of the present word and also the language model ranks the words according to their probability. within the case that no letters of the present word are entered, the language model is that the sole think about generating predictions. Systems usually use a touchscreen or function/number keys to pick any of the anticipated words. Because the goal of word prediction systems is to scale back the quantity of keystrokes, the first analysis for word prediction is keystroke savings (

Soft Computing

One of the most important ways to experience communication and interact with the systems is by handling the prediction of the most likely words to happen after typing letters or words. It is helpful for people with disabilities due to disabling people who could type or enter texts at a limited slow speed. Also, it is beneficial for people with dyslexia and those people who are not well with spells of words. Though, an input technology, for instance, the next word suggestion facilitates the typing process in smartphones as an example. This means that when a user types a word, then the system suggests the next words to be chosen in which the necessary word by the user. Besides, it can be used in entertainment as a gam, for example, to determine a target word and reach it or tackle it within 10 attempts of prediction. Generally, the systems depend on a text corpus, which was provided in the system to conduct the prediction. Writing every single word is time-consuming, therefore, it is vitally important to decrease time consumption by reducing efforts to input texts in the systems by offering most probable words for the user to select, this could be done via next word prediction systems. There are several techniques can be found in literature, which is utilized to conduct a variety of next word prediction systems by using different approaches. In this paper, a survey of miscellaneous techniques towards the next word prediction systems will be addressed. Besides, the evaluation of the prediction systems will be discussed. Then, a modal technique will be determined to be utilized for the next word prediction system from the perspective of easiness of implementation and obtaining a good result.

Universal Access in the Information Society, 2006

Text prediction is one of the most widely used techniques to enhance the communication rate in augmentative and alternative communication. Prediction systems are traditionally used by people with disabilities (e.g. people with motor and speech impairments). However, new applications, such as writing short text messages via mobile phones, have recently appeared. A vast amount of heterogeneous text prediction methods and techniques can be found in literature. Their heterogeneity makes it difficult to understand and compare them, in order to select the most convenient technique for a specific design. This paper presents a survey on text prediction techniques with the intention to provide a systematic view of this field. Prediction applications and related features, such as block size, dictionary structure, prediction method, user interface, etc., are examined. In addition, prediction measurement parameters and published results are compared. A large number of factors that may influence prediction results, including the acceptance of the system by the users, are reviewed, and their influence on the performance and usability of the system is discussed.

Research on computing science, 2008

Predictive text interfaces allow for text entry on mobile phones, using only a 12-key numeric keypad. While current predictive text sys- tems require only around 1 keystroke per character entered, there is ambiguity in the proposed words that must be resolved by the user. In word-based approaches to predictive text, a user enters a sequence of keystrokes and is presented with an ordered list of word proposals. The aim is to minimise the number of times a user has to cycle through incorrect proposals to reach their intended word. This paper considers how contextual information can be incorporated into this prediction process, while remaining viable for current mobile phone technology. Our hypothesis is that Transformation-Based Learn- ing is a natural choice for inducing predictive text systems. We show that such a system can: a) outperform current baselines; and b) correct common prediction errors such as "of" vs. "me" and "go" vs. "in".