Model Merging Versus Model Splitting Context-Free Grammar Induction

Menno Zaanen, Nanne Noord
Proceedings of the Eleventh International Conference on Grammatical Inference, PMLR 21:224-236, 2012.

Abstract

When comparing different grammatical inference algorithms, it becomes evident that generic techniques have been used in different systems. Several finite-state learning algorithms use state-merging as their underlying technique and a collection of grammatical inference algorithms that aim to learn context-free grammars build on the concept of substitutability to identify potential grammar rules. When learning context-free grammars, there are essentially two approaches: model merging, which generalizes with more data, and model splitting, which specializes with more data. Both approaches can be combined sequentially in a generic framework. In this article, we investigate the impact of different approaches within the first phase of the framework on system performance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v21-vanzaanen12b, title = {Model Merging Versus Model Splitting Context-Free Grammar Induction}, author = {Zaanen, Menno and Noord, Nanne}, booktitle = {Proceedings of the Eleventh International Conference on Grammatical Inference}, pages = {224--236}, year = {2012}, editor = {Heinz, Jeffrey and Higuera, Colin and Oates, Tim}, volume = {21}, series = {Proceedings of Machine Learning Research}, address = {University of Maryland, College Park, MD, USA}, month = {05--08 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v21/vanzaanen12b/vanzaanen12b.pdf}, url = {https://proceedings.mlr.press/v21/vanzaanen12b.html}, abstract = {When comparing different grammatical inference algorithms, it becomes evident that generic techniques have been used in different systems. Several finite-state learning algorithms use state-merging as their underlying technique and a collection of grammatical inference algorithms that aim to learn context-free grammars build on the concept of substitutability to identify potential grammar rules. When learning context-free grammars, there are essentially two approaches: model merging, which generalizes with more data, and model splitting, which specializes with more data. Both approaches can be combined sequentially in a generic framework. In this article, we investigate the impact of different approaches within the first phase of the framework on system performance.} }
Endnote
%0 Conference Paper %T Model Merging Versus Model Splitting Context-Free Grammar Induction %A Menno Zaanen %A Nanne Noord %B Proceedings of the Eleventh International Conference on Grammatical Inference %C Proceedings of Machine Learning Research %D 2012 %E Jeffrey Heinz %E Colin Higuera %E Tim Oates %F pmlr-v21-vanzaanen12b %I PMLR %P 224--236 %U https://proceedings.mlr.press/v21/vanzaanen12b.html %V 21 %X When comparing different grammatical inference algorithms, it becomes evident that generic techniques have been used in different systems. Several finite-state learning algorithms use state-merging as their underlying technique and a collection of grammatical inference algorithms that aim to learn context-free grammars build on the concept of substitutability to identify potential grammar rules. When learning context-free grammars, there are essentially two approaches: model merging, which generalizes with more data, and model splitting, which specializes with more data. Both approaches can be combined sequentially in a generic framework. In this article, we investigate the impact of different approaches within the first phase of the framework on system performance.
RIS
TY - CPAPER TI - Model Merging Versus Model Splitting Context-Free Grammar Induction AU - Menno Zaanen AU - Nanne Noord BT - Proceedings of the Eleventh International Conference on Grammatical Inference DA - 2012/08/16 ED - Jeffrey Heinz ED - Colin Higuera ED - Tim Oates ID - pmlr-v21-vanzaanen12b PB - PMLR DP - Proceedings of Machine Learning Research VL - 21 SP - 224 EP - 236 L1 - http://proceedings.mlr.press/v21/vanzaanen12b/vanzaanen12b.pdf UR - https://proceedings.mlr.press/v21/vanzaanen12b.html AB - When comparing different grammatical inference algorithms, it becomes evident that generic techniques have been used in different systems. Several finite-state learning algorithms use state-merging as their underlying technique and a collection of grammatical inference algorithms that aim to learn context-free grammars build on the concept of substitutability to identify potential grammar rules. When learning context-free grammars, there are essentially two approaches: model merging, which generalizes with more data, and model splitting, which specializes with more data. Both approaches can be combined sequentially in a generic framework. In this article, we investigate the impact of different approaches within the first phase of the framework on system performance. ER -
APA
Zaanen, M. & Noord, N.. (2012). Model Merging Versus Model Splitting Context-Free Grammar Induction. Proceedings of the Eleventh International Conference on Grammatical Inference, in Proceedings of Machine Learning Research 21:224-236 Available from https://proceedings.mlr.press/v21/vanzaanen12b.html.

Related Material