1 |
From Stance to Concern: Adaptation of Propositional Analysis to New Tasks and Domains ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Detecting Asks in SE attacks: Impact of Linguistic and Structural Knowledge ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Adaptation of a Lexical Organization for Social Engineering Detection and Response Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Citation Handling for Improved Summarization of Scientific Documents
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Measuring Variability in Sentence Ordering for News Summarization
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Challenges in Building an Arabic-English GHMT System with SMT Components
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Construction of a Chinese-English Verb Lexicon for Embedded Machine Translation in Cross-Language Information Retrieval
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Domain-Specific Term-List Expansion Using Existing Linguistic Resources
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Constraints on the Generation of Tense, Aspect, and Connecting Words from Temporal Expressions
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Handling Translation Divergences: Combining Statistical and Symbolic Techniques in Generation-Heavy Machine Translation
|
|
|
|
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, ource-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 overgeneration, which accounts for different possible translation divergences, is constrained by a statistical target-language model. (Also LAMP-TR-088) (Also UMIACS-TR-2002-49)
|
|
URL: http://hdl.handle.net/1903/1202
|
|
BASE
|
|
Hide details
|
|
16 |
Handling Translation Divergences in Generation-Heavy Hybrid Machine Translation
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Efficient Language Independent Generation from Lexical Conceptual Structures
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Lexical Resource Integration across the Syntax-Semantics Interface
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Mapping Lexical Entries in a Verbs Database to WordNet Senses
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Large Scale Language Independent Generation Using Thematic Hierarchies
|
|
|
|
BASE
|
|
Show details
|
|
|
|