http://hdl.handle.net/10398/83 2013-06-19T10:59:01Z 2013-06-19T10:59:01Z Buch-Kromann, Matthias Haulrich, Martin http://hdl.handle.net/10398/8221 2011-09-09T00:03:33Z 2010-12-14T00:00:00Z

Hierarchy-based Partition Models: Using Classification Hierarchies to Buch-Kromann, Matthias; Haulrich, Martin We propose a novel machine learning technique that can be used to estimate probability distributions for categorical random variables that are equipped with a natural set of classification hierarchies, such as words equipped with word class hierarchies, wordnet hierarchies, and suffix and affix hierarchies. We evaluate the estimator on bigram language modelling with a hierarchy based on word suffixes, using English, Danish, and Finnish data from the Europarl corpus with training sets of up to 1–1.5 million words. The results show that the proposed estimator outperforms modified Kneser-Ney smoothing in terms of perplexity on unseen data. This suggests that important information is hidden in the classification hierarchies that we routinely use in computational linguistics, but that we are unable to utilize this information fully because our current statistical techniques are either based on simple counting models or designed for sample spaces with a distance metric, rather than sample spaces with a non-metric topology given by a classification hierarchy. Keywords: machine learning; categorical variables; classification hierarchies; language modelling; statistical estimation

2010-12-14T00:00:00Z Buch-Kromann, Matthias http://hdl.handle.net/10398/8222 2012-01-09T09:46:33Z 2010-12-14T00:00:00Z

The DTAG treebank tool. Annotating and querying treebanks and Buch-Kromann, Matthias DTAG is a versatile annotation tool that supports manual and semi-automatic annotation of a wide range of linguistic phenomena, including the annotation of syntax, discourse, coreference, morphology, and word alignments. It includes commands for editing general labeled graphs and graph alignments, comparing annotations, managing annotation tasks, and interfacing with a revision control system. Its visualization component can display graphs and alignments for entire texts in a compact format, with a highly flexible and configurable formatting scheme. It also provides a powerful search-replace mechanism with queries based on full first-order logic, which can be used to search for linguistic constructions and automatically apply graph transformations to collections of annotated graphs.

2010-12-14T00:00:00Z Christiansen, Thomas U. http://hdl.handle.net/10398/8218 2010-12-09T09:04:30Z 2010-12-09T00:00:00Z

A Danish Nonsense Syllable Speech Material Christiansen, Thomas U. Nonsense syllable speech materials are often used when investigating speech perception in quiet and under adverse conditions. The main advantage of using nonsense syllables over words and sentences is that the acoustic as well as linguistic context is minimal. This paper describes the considerations involved in producing three anechoic recordings of 14 male and 14 female native talkers of Danish each speaking 65 nonsense syllables repeated three times with falling F0 (total of 16380 syllables).

2010-12-09T00:00:00Z Juel Henrichsen, Peter http://hdl.handle.net/10398/7763 2009-08-05T09:28:50Z 2009-04-07T13:28:51Z

The CBS Text-to-Speech Workbench Juel Henrichsen, Peter This working paper presents the CBS text-to-speech tool colloquially known as the TtT (Tekst-til-Tale). The tool is intended for training of university-level students, especially linguists training for a degree in speech technology, and visiting foreign students wanting to improve their spoken Danish. The TtT is operated through a simple wwwbased user-interface. Using the TtT requires basic skills in formal grammar-writing, but no knowledge on other aspects of artificial voice development such as phonetic-acoustic quantification, prosodic modelling, and signal generation. The paper includes a user manual.

2009-04-07T13:28:51Z