Comparison of alignment templates and maximum entropy models for natural language understanding

Authors:
Oliver Bender;Klaus Macherey;Franz Josef Och;Hermann Ney
Affiliations:
RWTH Aachen - University of Technology, Aachen, Germany;RWTH Aachen - University of Technology, Aachen, Germany;RWTH Aachen - University of Technology, Aachen, Germany;RWTH Aachen - University of Technology, Aachen, Germany
Venue:
EACL '03 Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - Volume 1
Year:
2003

Citing 7
Cited 6

The Philips automatic train timetable information system

Speech Communication - Special issue on interactive voice technology for telecommunication applications
A maximum entropy approach to natural language processing

Computational Linguistics
The mathematics of statistical machine translation: parameter estimation

Computational Linguistics - Special issue on using large corpora: II
Hidden understanding models of natural language

ACL '94 Proceedings of the 32nd annual meeting on Association for Computational Linguistics
A comparison of alignment models for statistical machine translation

COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 2
HMM-based word alignment in statistical translation

COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 2
Statistical natural language understanding using hidden clumpings

ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01

A maximum entropy approach to FrameNet tagging

NAACL-Short '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology: companion volume of the Proceedings of HLT-NAACL 2003--short papers - Volume 2
Maximum Entropy Modeling: A Suitable Framework to Learn Context-Dependent Lexicon Models for Statistical Machine Translation

Machine Learning
Maximum entropy models for FrameNet classification

EMNLP '03 Proceedings of the 2003 conference on Empirical methods in natural language processing
FrameNet-based semantic parsing using maximum entropy models

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Part-of-Speech Tagging Based on Machine Translation Techniques

IbPRIA '07 Proceedings of the 3rd Iberian conference on Pattern Recognition and Image Analysis, Part I
Joint identification and segmentation of domain-specific dialogue acts for conversational dialogue systems

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we compare two approaches to natural language understanding (NLU). The first approach is derived from the field of statistical machine translation (MT), whereas the other uses the maximum entropy (ME) framework. Starting with an annotated corpus, we describe the problem of NLU as a translation from a source sentence to a formal language target sentence. We mainly focus on the quality of the different alignment and ME models and show that the direct ME approach outperforms the alignment templates method.