International Journal of Computer Processing of Languages

An augmentative communication system is a blend of technology and language. The technology can be very light — a sheet of cardboard accessed by head stick or very complex — a computerized speech-generating device (SGD) accessed by infrared pointing. The language system, however, whether simply or intricately implemented, must be linguistically sophisticated from the beginning to allow the learner to become familiar with the distributional regularities of the language and give him/her the ability to construct utterances and have the chance to test them in his/her linguistic environment and adjust them to environmental requirements. A language system in AAC must include and join five aspects of language: the sound system (intonation/tone/pitch, stress, rhythm, homonymy), the grammatical structures (closed classes, word order, morphology, parts of speech, syntagmatic axis, paradigmatic axes), the vocabulary organization (word phrase definitions, word boundaries, semantic primitives and networks), the writing system (pinyin, simplified and traditional ideograms/logograms and their radicals, language representation methods), and the cultural outlook (form, meaning, and distribution of popular metaphors, pragmatics, folk metalinguistics, teaching practices, teaching materials). To this must be added concerns from theories of language growth and development including aphasias and learning disabilities. This paper is an overview of foundational issues involved in the development of a Mandarin language system for augmentative communication.

The purpose of this study is to clarify how Japanese and English speakers interpret picture-based sentences. Two studies were conducted, one with adults and one with children. The main task is to interpret eight picture-based sentences in two word-order conditions, SVO and SOV. These two conditions reflect the natural word orders of Japanese and English, respectively. The results suggest that word order was a more important cue for native English speakers than for native Japanese speakers in interpreting picture-based sentences. English speakers had more difficulty with picture symbols arrayed in SOV order than SVO. Japanese speakers had the most difficulty with missing syntactic particles in both word orders; successful interpretation sometimes depended on the particular meaning of the nouns and verbs in the sentences. This may be because English word order is more fixed, while Japanese word order has greater variance and capitalizes on syntax markers to clarify the meaning of a sentence.

Augmentative and Alternative Communication (AAC) computer-based systems are used by individuals with severe disabilities who cannot speak. AAC technology is designed with the goal to optimize communication and improve quality of life. This paper presents principles of design based on evidence-based practice (EBP) and language activity monitoring (LAM). When applied to the research and development of AAC computer-based technology, these principles provide quantitative data for making decisions about product performance and achievable outcomes focusing on the benefit to the end-user. The evaluation of a Mandarin language software application provides an example of how the steps of EBP and LAM data were applied during the initial research tasks. The EBP model offers a unique innovation to product development by challenging computer processing designers and programmers to design systematic and scientific data collection and analysis procedures specific to EBP.

A fundamental understanding of the underlying clinical intervention and acquisition process of an Augmentative and Alternative Communication (AAC) system is crucial in its development. In this paper, we attempt to document the beginning stages of teaching, intervention methods and outcomes of a Mandarin Chinese (MC) and an English speaker as they acquire communicative competence of their AAC system. The system for the MC speaker comprised a low tech communication chart and a notepad for writing. The English speaker used a high tech voice output device based on semantic compaction. Preliminary data on outcomes of the first three months of training was gathered, and interpreted. This paper attempts to analyze these two outcomes and discuss potential issues arising from this experience. It will also address implications for further training and the development of a high tech voice output MC AAC system.

Augmentative and alternative communication (AAC) technology for the speech-impaired has been successfully implemented in America and Europe using semantic compaction theory, combined with multi-meaning icons, to create a natural language representation paired with a speech synthesizer. Analogous technology is now under development for Mandarin Chinese (MC) speaking users. Any effective AAC device using semantic compaction must have a well-designed keyboard, or overlay, for access to the stored language. The design of this overlay comprises several icon design steps, including grammar representation, polysemous (multi-meaning) icons, and culture-specific revisions. When completed, the overlay for a Mandarin AAC system should be both derived from the successful systems of the past, and uniquely optimized for Chinese speakers.

Creating a generative language system in augmentative and alternative communication (AAC) for both literate and non-literate users requires three fundamental design steps: analyzing the grammar of the language; developing an efficient, culturally relevant pictorial representation system for encoding the language; and selecting a list of target words to encode. This paper will focus on the problem of selecting vocabulary for the AAC system. This is an important problem because the selection of the encoded vocabulary will ultimately determine the language coverage of the AAC system. The vocabulary list should provide coverage on three fronts: it should contain the most frequently used vocabulary of the spoken language; it should allow description of all the universal, fundamental semantic concepts; and it should meet users' expectations of what they should be able to say on a daily basis, in any given situation. Mandarin Chinese, as a relatively new target language for AAC, presents some unique challenges to the vocabulary designers. For example, the conceptual differences between the Chinese word and character can be difficult to pin down; this highlights the importance of a consistent and scientific approach to vocabulary selection. This paper describes the research process used in the creation of a core vocabulary list for a new icon-encoded Mandarin Chinese AAC system, starting with a basic corpus-derived word-frequency list, and continuing with the modification and supplementation of this list with other linguistic and anecdotal knowledge.