For automatic speech recognition, the construction of an adequate language model may be difficult when only a limited amount of training text is available. Previous work has shown that in the case of small training sets statistical language models may outperform grammars on out-of-coverage utterances, while showing comparable performance on incoverage input. In this paper, we compare the perfor...

Texts exchanged in business-related Computer-Mediated Communication, or CMC, differ from texts exchanged in other business situations. CMC data have a high concentration of non-standard textual features. The fast-growing amount of business CMC data offers opportunities for the application of statistical Natural Language Processing and Machine Learning methods, especially for text-classification...

In natural language generation using symbolic grammars, state-of-the-art realisation rankers use statistical models incorporating both language model and structural features. The rankers depend on multiple structures produced by the particular large-scale symbolic grammars to rank the output; for languages with smaller resources and in-development grammars, we look at the feasibility of an alte...

This work combines grammars and statistical language models for speech recognition together in the same sentence. The grammars are compiled into bigrams with word indices, which serve to distinguish different syntactic positions of the same word. For both the grammatical and statistical parts there is one common interface for obtaining a language model score for bior trigrams. With only a small...

Parsing is an important process of Natural Language Processing (NLP) and Computational Linguistics which is used to understand the syntax and semantics of a natural language sentences confined to the grammar. Parser is a computational system which processes input sentence according to the productions of the grammar, and builds one or more constituent structures which conform to the grammar. The...

I design computationally intensive statistical methods for the discovery of syntactic and semantic structure in natural language text. A major focus of my research is on the use of both linguistically annotated as well as unannotated textual data, from which the aforementioned statistical models are estimated. My work has resulted in significant improvements in shallow semantic parsing of text ...

Statistical language models have gained a reputation as providing the overall performance for speech recognition, and so widely used in speech recognition systems today. The tasks to which statistical language models can be applied are, however, limited, because a large corpus is essential for the building of a statistical model, and the collection of a new corpus is a very costly task in terms...

We introduce the Rel-grams language model, which is analogous to an n-grams model, but is computed over relations rather than over words. The model encodes the conditional probability of observing a relational tuple R, given that R′ was observed in a window of prior relational tuples. We build a database of Rel-grams co-occurence statistics from ReVerb extractions over 1.8M news wire documents ...

Information Retrieval (IR) is an important application area of Natural Language Processing (NLP) where one encounters the genuine challenge of processing large quantities of unrestricted natural language text. While much effort has been made to apply NLP techniques to IR, very few NLP techniques have been evaluated on a document collection larger than several megabytes. Many NLP techniques are ...