373 search results - page 2 / 75 » Trainable Methods for Surface Natural Language Generation |
ACL
2010
14 years 7 months ago
2010
Most previous work on trainable language generation has focused on two paradigms: (a) using a statistical model to rank a set of generated utterances, or (b) using statistics to i...
ANLP
2000
14 years 11 months ago
2000
Bagging and boosting, two effective machine learning techniques, are applied to natural language parsing. Experiments using these techniques with a trainable statistical parser ar...
NLPRS
2001
Springer
15 years 2 months ago
2001
Springer
This paper describes a method of extracting katakana words and phrases, along with their English counterparts from non-aligned monolingual web search engine query logs. The method...
HASKELL
2006
ACM
15 years 3 months ago
2006
ACM
In this article we present GenI, a chart based surface realisation tool implemented in Haskell. GenI takes as input a set of first order terms (the input semantics) and a grammar...
ACL
1998
14 years 11 months ago
1998
Determining the attachments of prepositions and subordinate conjunctions is a key problem in parsing natural language. This paper presents a trainable approach to making these att...