We show that transductive (cross-domain) learning is an important consideration in building a general-purpose language identification system, and develop a feature selection method that generalizes across domains. Our results demonstrate that our method provides improvements in transductive transfer learning for language identification. We provide an implementation of the method and show that o...

This paper demonstrates that design and implementation of languages for a speciic domain can be done on a very high level of abstraction: elements and properties of a language are composed mainly by simple yes/no decisions. Consistency and completeness of the decisions are automatically checked. An implementation of the chosen language is obtained by selecting com-binable speciication component...

An evolutionary model for emergence of diversity in language is developed. We investigated the effects of two real life observations, namely, people prefer people that they communicate with well, and people interact with people that are physically close to each other. Clearly these groups are relatively small compared to the entire population. We restrict selection of the teachers from such sma...

Content Determination (aka Content Selection)

About 1 in 5 Americans have some kind of disability, and 1 in 10 have a severe disability (McNiel, 1997). Intelligent environments can augment lost abilities, but they depend upon speech recognition. Unfortunately, current speech recognition systems are not accurate enough for common use. A home environment was instrumented with home automation devices, motion detectors, and a speech recognitio...

The Moore-Lewis method of"intelligent selection of language model training data"is very effective, cheap, efficient... and also has structural problems. (1) The method defines relevance by playing language models trained on the in-domain and the out-of-domain (or data pool) corpora against each other. This powerful idea-- which we set out to preserve-- treats the two corpora as the opposing end...

Switch costs are generally found in language switching tasks. However, the locus where switch costs occur during bilingual language production remains unclear. Several studies that used a cued language-switching paradigm have attempted to investigate this question in bilingual language production, but researchers have not reached a consensus. Moreover, we are interested in where switch costs oc...

Data selection is an effective approach to domain adaptation in statistical machine translation. The idea is to use language models trained on small in-domain text to select similar sentences from large general-domain corpora, which are then incorporated into the training data. Substantial gains have been demonstrated in previous works, which employ standard ngram language models. Here, we expl...

Janssen and Caramazza (2003) show that when producing diminutives or plurals in Dutch, determiner information about the corresponding (singular) base form is active. This is reflected in a time cost for producing the plural or the diminutive with a gender-marked determiner when these forms and the corresponding singular or base form require different determiners. No such cost is observed when s...