Oxygen: A Language Independent Linerization Engine

reportActive / Technical Report | Accession Number: ADA458719 | Open PDF

Abstract:

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 have been used successfully in creating an English linearization program that is currently used as part of a Chinese-English machine translation system.

Author(s):
Habash, Nizar
Author Organization(s):
MARYLAND UNIV COLLEGE PARK INST FOR ADVANCED COMPUTER STUDIES
Descriptive Note:
Technical rept.
Supplementary Note:
Sponsored in part under NSF grant EIA0130422. UMIACS-2000-35. The original document contains color images. DOI: 10.21236/ADA458719
Pagination:
0012

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

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

RECORD

Collection: TR
Identifying Numbers
Report Number(s):
LAMP-TR-042, CS-TR-4144
Contract/Grant Number(s):
MDA9049-C6-1250
Monitor Series:
DOD
 Subject Terms
Joint Capability Areas:
JCA_8_Building Partnerships; JCA_8.2_Shape; JCA_8.1_Communicate; JCA_8.1.3_Influence Adversary and Competitor Audiences; JCA_8.2.1_Partner with Governments and Institutions; JCA_8.2.2_Provide Aid to Foreign Partners and Institutions; JCA_1_Force Support; JCA_1.2_Force Preparation; JCA_1.2.6_Concepts; JCA_1.2.3_Educating; JCA_5_Command and Control; JCA_5.3_Planning
Communities of Interest:
No COI(s) Identified
Descriptor(s):
*COMPUTER PROGRAMS, *SYNTAX, *NATURAL LANGUAGE, *GRAMMARS, LINEAR SYSTEMS, GRAPHS, ENGLISH LANGUAGE, CHINESE LANGUAGE, RULE BASED SYSTEMS, WORDS(LANGUAGE), STATISTICAL PROCESSES, LANGUAGE TRANSLATION
Field(s)/Group(s):
Linguistics
Keyword(s):
*LINEARIZATION ENGINES, *OXYGEN ENGINES(LINGUISTICS), OXYL SYNTAX, STATISTICAL EXTRACTION MODULES, NITROGEN ENGINES(LINGUISTICS), WORD LATTICES
Report Date:
2000 Jun 01
Creation Date:
2006 Dec 27