Oxygen: A Language Independent Linearization Engine
暂无分享,去创建一个
This paper describes a language independent linearization engine, oxyGen. This system compiles target language grammars into programs that take feature graphs as inputs and generate word lattices that can be passed along to the statistical extraction module of the generation system Nitrogen. The grammars are written using a flexible and powerful language, oxyL, that has the power of a programming language but focuses on natural language realization. This engine has been used successfully in creating an English linearization program that is currently employed as part of a Chinese-English machine translation system.
[1] Nizar Habash,et al. Generation from Lexical Conceptual Structures , 2000 .
[2] Vasileios Hatzivassiloglou,et al. Two-Level, Many-Paths Generation , 1995, ACL.
[3] Nizar Habash,et al. A thematic hierarchy for efficient generation from lexical-conceptual structure , 1998, AMTA.
[4] Kevin Knight,et al. The Practical Value of N-Grams Is in Generation , 1998, INLG.
[5] Kevin Knight,et al. Generation that Exploits Corpus-Based Statistical Knowledge , 1998, ACL.