Automatic resolution of segmentation ambiguities in grammar authoring
作者： YeYi Wang , Alejandro Acero
DOI:
关键词:
摘要: A rules-based grammar is generated. Segmentation ambiguities are identified in training data. Rewrite rules for the ambiguous segmentations enumerated and probabilities generated each. Ambiguities resolved based on probabilities. In one embodiment, this done by applying expectation maximization (EM) algorithm.
lens.org 参考文章(18)
Xiaolong Mou, Ye-Yi Wang, Xuedong D Huang, Milind V Mahajan, Creating a unified task dependent language models with information retrieval techniques ,(2001)
Henry Spalding Baird, Tin Kam Ho, Methods and apparatus for classification of images using distribution maps ,(1994)
Fuliang Weng, Michael H. Cohen, Eric G. Jackson, Method and system for building and running natural language understanding systems ,(1995)
David Neal Weise, Method and apparatus for improved grammar checking using a stochastic parser ,(2005)
Kevin L. Markey, Edward A. Green, Ramon Krosley, Method and apparatus for normalizing and converting structured content ,(2001)
Milind Mahajan, Ciprian Chelba, Applying a structured language model to information extraction ,(2010)
Giuseppe Riccardi, Roberto Pieraccini, Enrico Bocchieri, Stochastic automata for language modeling Computer Speech & Language. ,vol. 10, pp. 265- 293 ,(1996) , 10.1006/CSLA.1996.0014
Scott Miller, Robert Bobrow, Robert Ingria, Richard Schwartz, Hidden understanding models of natural language Proceedings of the 32nd annual meeting on Association for Computational Linguistics -. pp. 25- 32 ,(1994) , 10.3115/981732.981736
Ye-Yi Wang, A. Acero, Grammar learning for spoken language understanding ieee automatic speech recognition and understanding workshop. pp. 292- 295 ,(2001) , 10.1109/ASRU.2001.1034645
Alex Acero, Ye-Yi Wang, Combination of CFG and n-gram modeling in semantic grammar learning. conference of the international speech communication association. pp. 2809- 2812 ,(2003)