Training Tree Transducers

reportActive / Technical Report | Accession Number: ADA460355 | Open PDF

Abstract:

Many probabilistic models for natural language are now written in terms of hierarchical tree structure. Tree-based modeling still lacks many of the standard tools taken for granted in finite-state string-based modeling. The theory of tree transducer automata provides a possible framework to draw on, as it has been worked out in an extensive literature. We motivate the use of tree transducers for natural language and address the training problem for probabilistic tree-to-tree and tree-to-string transducers.

Author(s):
Graehl, Jonathan ; Knight, Kevin
Author Organization(s):
UNIVERSITY OF SOUTHERN CALIFORNIA MARINA DEL REY INFORMATION SCIENCES INST
Descriptive Note:
Conference paper
Supplementary Note:
Presented at The Human Language Technology and North American Chapter of the Association for Computational Linguistics Conference (HLT-NAACL), held in Boston, MA on 2-5 May, 2004. Pub. in the Proceedings of The Human Language Technology and North American Chapter of the Association for Computational Linguistics Conference (HLT-NAACL), 2004. Sponsored in part by Advanced Research and Development Activity (ARDA), Ft. Meade, MD.
Pagination:
0009

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution:
Approved For Public Release
Distribution Statement:
Approved For Public Release; Distribution Is Unlimited.

RECORD

Collection: TR
Identifying Numbers
Contract/Grant Number(s):
F49620-00-1-0337, MDA904-02-C-450
Monitor Series:
DARPA
 Subject Terms
Joint Capability Areas:
JCA_1_Force Support; JCA_1.2_Force Preparation; JCA_1.2.1_Training; JCA_1.3_Human Capital Management; JCA_1.3.1_Personnel and Family Support; JCA_5_Command and Control; JCA_5.2.2_Develop Knowledge and Situational Awareness; JCA_5.2_Understand; JCA_1.2.3_Educating; JCA_6_Net Centric; JCA_8_Building Partnerships
Modernization Areas:
AI and Machine Learning
Communities of Interest:
Energy and Power Technologies
Descriptor(s):
*MATHEMATICAL MODELS, *TRAINING, *HIERARCHIES, *NATURAL LANGUAGE, *TRANSDUCERS, ALGORITHMS, MACHINE TRANSLATION, AUTOMATA, GRAMMARS, PARSERS, INPUT OUTPUT MODELS, SPEECH RECOGNITION, PROBABILITY, SYMPOSIA
Field(s)/Group(s):
Linguistics, Cybernetics
Keyword(s):
*TREE TO STRING TRANSDUCERS, *TREE TO TREE TRANSDUCERS, FINITE STATE TRANSDUCERS, FTS(FINITE STATE TRANSDUCERS), R TRANSDUCERS, ROOT TO FRONTIER TRANSDUCERS, RTG(REGULAR TREE GRAMMAR), ESTIMATION MAXIMIZATION TRAINING
Report Date:
2004 Jan 01
Creation Date:
2007 Jan 31