Sciweavers

Share
ACL
2012
8 years 2 months ago
Prediction of Learning Curves in Machine Translation
Parallel data in the domain of interest is the key resource when training a statistical machine translation (SMT) system for a specific purpose. Since ad-hoc manual translation c...
Prasanth Kolachina, Nicola Cancedda, Marc Dymetman...
ICDT
2011
ACM
242views Database» more  ICDT 2011»
9 years 3 months ago
Knowledge compilation meets database theory: compiling queries to decision diagrams
The goal of Knowledge Compilation is to represent a Boolean expression in a format in which it can answer a range of online-queries in PTIME. The online-query of main interest to ...
Abhay Kumar Jha, Dan Suciu
ICASSP
2011
IEEE
9 years 3 months ago
Score fusion and calibration in multiple language detectors with large performance variation
In a large-scale language detection task, performance variation found between different component systems and different target languages has an adverse effect to the pooled error ...
Raymond W. M. Ng, Cheung-Chi Leung, Tan Lee, Bin M...
ACL
2011
9 years 3 months ago
Combining Morpheme-based Machine Translation with Post-processing Morpheme Prediction
This paper extends the training and tuning regime for phrase-based statistical machine translation to obtain fluent translations into morphologically complex languages (we build ...
Ann Clifton, Anoop Sarkar
COLING
2010
9 years 6 months ago
Automated Translation of Semantic Relationships
We present a method for translating semantic relationships between languages where relationships are defined as pattern clusters. Given a pattern set which represents a semantic r...
Dmitry Davidov, Ari Rappoport
INFORMATICALT
2000
114views more  INFORMATICALT 2000»
9 years 11 months ago
The Language-Centric Program Generator Models: 3L Paradigm
Abstract. In this paper we suggest a three-language (3L) paradigm for building the program generator models. The basis of the paradigm is a relationship model of the specification,...
Vytautas Stuikys, Giedrius Ziberkas, Robertas Dama...
JSAT
2006
126views more  JSAT 2006»
9 years 11 months ago
Complexity Results for Quantified Boolean Formulae Based on Complete Propositional Languages
Several propositional fragments have been considered so far as target languages for knowledge compilation and used for improving computational tasks from major AI areas (like infe...
Sylvie Coste-Marquis, Daniel Le Berre, Florian Let...
ACL
1997
10 years 1 months ago
Ambiguity Resolution for Machine Translation of Telegraphic Messages
Telegraphic messages with numerous instances of omission pose a new challenge to parsing in that a sentence with omission causes a higher degree of ambi6uity than a sentence witho...
Young-Suk Lee, Clifford J. Weinstein, Stephanie Se...
LREC
2010
221views Education» more  LREC 2010»
10 years 1 months ago
KALAKA: A TV Broadcast Speech Database for the Evaluation of Language Recognition Systems
A speech database, named KALAKA, was created to support the Albayzin 2008 Evaluation of Language Recognition Systems, organized by the Spanish Network on Speech Technologies from ...
Luis Javier Rodríguez-Fuentes, Mikel Pe&nti...
ERSHOV
2006
Springer
10 years 1 months ago
On the Usage of Concrete Syntax in Model Transformation Rules
Graph transformations are one of the best known approaches for defining transformations in model-based software development. They are defined over the abstract syntax of source and...
Thomas Baar, Jon Whittle
books