Browsing by Author "Haulrich, Martin"
Now showing items 1-2 of 2
-
Haulrich, Martin (Frederiksberg, 2012)[More information][Less information]
Abstract: Parallel treebanks have received increasing attention in the past few years, primarily due to their potential use in statistical machine translation. Creating parallel treebanks manually is a time-consuming and expensive task and for this reason there is considerable interest in creating treebanks automatically. This task can be solved using standard tools such as parsers and aligners. However, because parallel treebanks are based on parallel corpora, we are in a special situation where the same meaning is represented in two different ways. This thesis is about how we can exploit this information to create better parallel treebanks than we can by using standard tools.... URI: http://hdl.handle.net/10398/8385 Files in this item: 1
Martin_Haulrich.pdf (1.932Mb) -
Buch-Kromann, Matthias; Haulrich, Martin (Frederiksberg, 2010)[More information][Less information]
Abstract: 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 URI: http://hdl.handle.net/10398/8221 Files in this item: 1
2010-wp-buch-kromann-haulrich.pdf (216.6Kb)
Now showing items 1-2 of 2