Searching for authors named "Miles Osborne" – sorted by Relevance.
-
Estimation of Stochastic Attribute-Value Grammars using an Informative Sample
- We argue that some of the computational complexity associated with estimation of stochastic attribute- value grammars can be reduced by training upon an informative subset of the full training set. Results using the t)arsed Wall Street Journal tort)us show that in some circumstances, it is possible
- Cited by 6 (1 self) – Add To MetaCart
-
Just how good is maximum entropy? An empirical investigation using ensembles of MEMD models for attribute-value grammars
- Maximum entropy has been theoretically argued as being the principled way to estimate models that are only partially determined by some set of empirically observed constraints. However, such arguments hinge upon large sample behaviour, and it is unclear how well maximum entropy performs when this as
- Cited by 3 (0 self) – Add To MetaCart
-
Can Punctuation Help Learning?
- The quality of learnt natural language grammars can be enhanced by exploiting the linguistic devices that comprise a corpus. This paper considers one such device, namely punctuation. After briefly considering the linguistics of punctuation, a model capturing some of these properties is presente
- Cited by 1 (1 self) – Add To MetaCart
-
Shallow Parsing as Part-of-Speech Tagging
- Treating shallow parsing as part-of-speech tagging yields results comparable with other, more elaborate approaches. Using the CoNLL 2000 training and testing material, our best model had an accuracy of 94.88%, with an overall FB1 score of 91.94%. The individual FB1 scores for NPs were 92.19%, VPs 92
- Cited by 6 (0 self) – Add To MetaCart
-
MDL-based DCG Induction for NP Identification
- We introduce a learner capable of automatically extend- ing large, manually written natural language Definite Clause Grammars with missing syntactic rules. It is based upon the Minimum Description Length principle, and can be trained upon either just raw text, or else raw text additionally annotated
- Cited by 6 (3 self) – Add To MetaCart
-
DCG Induction using MDL and Parsed Corpora
- We show how partial models of natural language syntax (manually written DCGs, with parameters estimated from a parsed corpus) can be automatically extended when trained upon raw text (using MDL). We also show how we can use a parsed corpus as an alternative constraint upon learning. Empirical ev
- Cited by 3 (2 self) – Add To MetaCart
-
Minimisation, Indifference and Statistical Language Learning
- When applied to probabilistic categorial grammar learning, the Minimum Description Length principle outperforms Maximum Likelihood Estimation. Smoothing does not bridge the gap between the two approaches.
- Cited by 2 (0 self) – Add To MetaCart
-
Predicting Success in Machine Translation
- The performance of machine translation systems varies greatly depending on the source and target languages involved. Determining the contribution of different characteristics of language pairs on system performance is key to knowing what aspects of machine translation to improve and which are irrele
- Add To MetaCart
-
Modelling lexical redundancy for machine translation
- Certain distinctions made in the lexicon of one language may be redundant when translating into another language. We quantify redundancy among source types by the similarity of their distributions over target types. We propose a languageindependent framework for minimising lexical redundancy that ca
- Cited by 4 (1 self) – Add To MetaCart
-
Processing Natural Language Software Requirement Specifications
- Ambiguity in requirement specifications causes numerous problems
- Cited by 13 (1 self) – Add To MetaCart

