This paper describes a multi-domain text-to-speech (MD-TTS) synthesis strategy for generating speech among different domains and so increasing the flexibility of high quality TTS systems. To that effect, the MD-TTS introduces a flexible TTS architecture that includes an automatic domain classification module, which allows MD-TTS systems to be implemented by different synthesis strategies and sp...

The robustness of n-gram language models depends on the quality of text data on which they have been trained. The text corpora collected from various resources such as web pages or electronic documents are characterized by many possible topics. In order to build efficient and robust domain-specific language models, it is necessary to separate domain-oriented segments from the large amount of te...

We propose a verb suggestion method which uses candidate sets and domain adaptation to incorporate error patterns produced by ESL learners. The candidate sets are constructed from a large scale learner corpus to cover various error patterns made by learners. Furthermore, the model is trained using both a native corpus and the learner corpus via a domain adaptation technique. Experiments on two ...

Due to the fact that emergency situations can lead to substantial losses, both financial and in terms of human lives, it is essential that texts used in a crisis situation be clearly understandable. This thesis is concerned with the study of the complexity of the crisis management sub-language and with methods to produce new, clear texts and to rewrite pre-existing crisis management documents w...

Over the past twenty-five years, researchers have expressed considerable interest in titles of academic publications. Unfortunately, conference paper titles (CPTs) have only recently begun to receive attention. The aim of this study, therefore, is to investigate the text length, syntactic structure, and lexicon of CPTs in Applied Linguistics. A data set of 698 titles was selected from the 2008 ...

Over the past twenty-five years, researchers have expressed considerable interest in titles of academic publications. Unfortunately, conference paper titles (CPTs) have only recently begun to receive attention. The aim of this study, therefore, is to investigate the text length, syntactic structure, and lexicon of CPTs in Applied Linguistics. A data set of 698 titles was selected from the 2008 ...

Words often gain new senses in new domains. Being able to automatically identify, from a corpus of monolingual text, which word tokens are being used in a previously unseen sense has applications to machine translation and other tasks sensitive to lexical semantics. We define a task, SENSESPOTTING, in which we build systems to spot tokens that have new senses in new domain text. Instead of diff...