EACL 2003 Workshop on

Language Modeling for Text Entry Methods

April 14, 2003, Budapest, Hungary

The EACL 2003 Workshop on Language Modeling for Text Entry Methods will be hosted in conjunction with the 10th Conference of the European Chapter of the Association for Computational Linguistics that will take place April 12-17, 2003, in Budapest, Hungary.

General Scope

There are two application areas where there is a strong need to support the user in text production:

• On palm-sized or watch-sized electronic devices, the physical size of the device and/or the available keyboard makes typing difficult and thus inefficient.
• For motor and/or speech impaired persons, typing often is slow or very difficult. This is critical especially for people relying on communication aids.

In both application areas, various text entry methods have been suggested to provide a more efficient input of texts with lower motor demands. Usually, they combine specific typing devices (enhancing the typing rate) with methods that aim at reducing the number of necessary key strokes. Among these are word prediction, abbreviation expansion, ambiguous typing and text compansion.

At their core, these methods rely on statistical and (to a lesser extent) rule-based language models to predict and complete the user input and thus save keystrokes. Unlike in speech recognition, the language models are also used to change and evaluate the way how to enter text.

The goal of our workshop is to bring together researchers in the two application communities to focus on the variety of text entry methods with language models. In particular, we like to discuss parameters and criteria for a comparable evaluation of text entry methods with language models. Questions of interest include but are not limited to:

• How are text entry methods improved by language models?
• At which linguistic levels do language models improve text entry methods?
• In what way should the language model adapt to the user's text entry?
• How can the added cognitive load of using text entry methods be minimized?
• What kind of resources (e.g. corpora, lexica) are needed for text entry methods with language models?
• How can we evaluate and compare text entry methods with language models?
• Where do situational contexts lead to better language models for text entry methods?
• What are the specifics of language models for text entry methods in particular languages and writing systems?

Although there has been some transfer of technology between the two application areas, communication between the two research communities has been sparse up to now. We invite researchers of the different application areas to share their results and ideas with the other communities in computational linguistics.

Workshop Program

Registration

Registration information is available at the EACL03 registration web page.

Programme Committee

Workshop Chairs

Further Information

Contact Information