Sciweavers

576 search results - page 74 / 116
» A Market-based Rule Learning System
Sort
View
104
Voted
EACL
2003
ACL Anthology
15 years 2 months ago
Empirical Methods for Compound Splitting
Compounded words are a challenge for NLP applications such as machine translation (MT). We introduce methods to learn splitting rules from monolingual and parallel corpora. We eva...
Philipp Koehn, Kevin Knight
125
Voted
ICADL
2003
Springer
159views Education» more  ICADL 2003»
15 years 6 months ago
Ontology Learning for Medical Digital Libraries
Ontologies play an important role in the Semantic Web as well as in digital library and knowledge portal applications. This project seeks to develop an automatic method to enrich e...
Chew-Hung Lee, Jin-Cheon Na, Christopher S. G. Kho...
57
Voted
ASPLOS
2006
ACM
15 years 6 months ago
Automatic generation of peephole superoptimizers
Peephole optimizers are typically constructed using human-written pattern matching rules, an approach that requires expertise and time, as well as being less than systematic at ex...
Sorav Bansal, Alex Aiken
OGAI
1993
15 years 4 months ago
Combining Neural Networks and Fuzzy Controllers
Fuzzy controllers are designed to work with knowledge in the form of linguistic control rules. But the translation of these linguistic rules into the framework of fuzzy set theory ...
Detlef Nauck, Frank Klawonn, Rudolf Kruse
93
Voted
EMNLP
2009
14 years 10 months ago
Weighted Alignment Matrices for Statistical Machine Translation
Current statistical machine translation systems usually extract rules from bilingual corpora annotated with 1-best alignments. They are prone to learn noisy rules due to alignment...
Yang Liu, Tian Xia, Xinyan Xiao, Qun Liu