DE eng

Search in the Catalogues and Directories

Hits 1 – 15 of 15

1
Annotation Guidelines for Arabic Nominal Gender, Number, and Rationality
Habash, Nizar Y.; Alkuhlani, Sarah M.. - : Center for Computational Learning Systems, Columbia University, 2013
BASE
Show details
2
Annotation Guidelines for Arabic Nominal Gender, Number, and Rationality ...
Habash, Nizar Y.; Alkuhlani, Sarah M.. - : Columbia University, 2013
BASE
Show details
3
Can Automatic Post-Editing Make MT More Meaningful?
BASE
Show details
4
Can Automatic Post-Editing Make MT More Meaningful? ...
McKeown, Kathleen; Parton, Kristen; Habash, Nizar Y.. - : Columbia University, 2012
BASE
Show details
5
Use of Minimal Lexical Conceptual Structures for Single-Document Summarization
In: DTIC (2004)
BASE
Show details
6
Symbolic MT With Statistical NLP Components
In: DTIC (2004)
BASE
Show details
7
A Categorial Variation Database for English
In: DTIC (2003)
BASE
Show details
8
Handling Translation Divergences in Generation-Heavy Hybrid Machine Translation
In: DTIC (2002)
BASE
Show details
9
Improved Word-Level Alignment: Injecting Knowledge about MT Divergences
In: DTIC (2002)
BASE
Show details
10
Handling Translation Divergences: Combining Statistical and Symbolic Techniques in Generation-Heavy Machine Translation
In: DTIC (2002)
Abstract: This paper describes a novel approach to handling translation divergences in a Generation-Heavy Hybrid Machine Translation (GHMT) system. The translation divergence problem is usually reserved for Transfer and Interlingual MT because it requires a large combination of complex lexical and structural mappings. A major requirement of these approaches is the accessibility of large amounts of explicit symmetrical knowledge for both source and target languages. This limitation renders Transfer and Interlingual approaches ineffective in the face of structurally-divergent language pairs with asymmetrical resources. GHMT addresses the more common form of this problem, source-poor/target-rich, by fully exploiting symbolic and statistical target-language resources. This is accomplished by using target-language lexical semantics, categorial variations and subcategorization frames to overgenerate multiple lexico-structural variations from a target-glossed syntactic dependency of the source-language sentence. The symbolic over-generation, which accounts for different possible translation divergences, is constrained by a statistical target-language model. ; Sponsored in part under NSF grant EIA0130422. Report No. UMIACS-TR-2002-49.
Keyword: *LEXICOGRAPHY; *MACHINE TRANSLATION; *MATHEMATICAL MODELS; *SEMANTICS; ASYMMETRY; CLASSIFICATION; Computer Programming and Software; FRAMES; GHMT(GENERATION HEAVY HYBRID MACHINE TRANSLATION); HANDLING; INTERLINGUAL MODELS; Linguistics; MAPPING; PROGRAMMING LANGUAGES; STATISTICAL PROCESSES; STATISTICAL TARGET LANGUAGE MODELS; SUBCATEGORIZATION; SYMBOLIC PROGRAMMING; SYMBOLIC TECHNIQUES; SYNTAX; TRANSFER MODELS; TRANSLATION DIVERGENCIES; WORDS(LANGUAGE)
URL: http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA458925
http://www.dtic.mil/docs/citations/ADA458925
BASE
Hide details
11
Efficient Language Independent Generation from Lexical Conceptual Structure
In: DTIC (2001)
BASE
Show details
12
Generation from Lexical Conceptual Structures
In: DTIC (2001)
BASE
Show details
13
Large Scale Language Independent Generation Using Thematic Hierarchies
In: DTIC (2001)
BASE
Show details
14
Nuun: A System for Developing Platform and Browser Independent Arabic Web Applications
In: DTIC (2001)
BASE
Show details
15
Oxygen: A Language Independent Linerization Engine
In: DTIC (2000)
BASE
Show details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
15
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern