In spoken document retrieval, speech recognition is applied to a collection to obtain either words or subword units, such as phonemes, that can be matched against queries. We have explored retrieval based on phoneme n-grams. The use of phonemes addresses the out-of-vocabulary problem, while use of n-grams allows approximate matching on inaccurate phoneme transcriptions. Our experiments explored...

There is an inherent redundancy in natural languages whereby certain common phrases (or n-grams) appear frequently in general sentences, each time with the same syntactic analysis. We explore the idea of exploiting this redundancy by pre-constructing the parse structures for these frequent n-grams. When parsing sentences in the future, the parser does not have to re-derive the parse structure f...

We propose the “advanced” n-grams as a new technique for simulating user behaviour in spoken dialogue systems, and we compare it with two methods used in our prior work, i.e. linear feature combination and “normal” n-grams. All methods operate on the intention level and can incorporate speech recognition and understanding errors. In the linear feature combination model user actions (lists of 〈 ...

Data sparsity is a large problem in natural language processing that refers to the fact that language is a system of rare events, so varied and complex, that even using an extremely large corpus, we can never accurately model all possible strings of words. This paper examines the use of skip-grams (a technique where by n-grams are still stored to model language, but they allow for tokens to be ...

Most icon-based augmentative and alternative communication (AAC) devices require users to formulate messages in syntactic order in order to produce syntactic utterances. Reliance on syntactic ordering, however, may not be appropriate for individuals with limited or emerging literacy skills. Some of these users may benefit from unordered message formulation accompanied by automatic message expan...

There are many ways to profile a collection of documents. This paper presents highlight from a body of work that has looked at individual differences in the language of personal weblogs. Firstly, we present a unitary measure of linguistic contextuality based on POS frequency that can be used to profile and rank genres. When applied to weblogs, we will show they are similar to school essays, yet...

Teachers/lecturers typically adapt their teaching to respond to students’ emotions, e.g. provide more examples when they think the students are confused. While getting a feel of the students’ emotions is easier in small settings, it is much more difficult in larger groups. In these larger settings textual feedback from students could provide information about learning-related emotions that stud...