Sciweavers

349 search results - page 13 / 70
» Training a Natural Language Generator From Unaligned Data
Sort
View
128
Voted
ACL
2012
13 years 6 months ago
Large-Scale Syntactic Language Modeling with Treelets
We propose a simple generative, syntactic language model that conditions on overlapping windows of tree context (or treelets) in the same way that n-gram language models condition...
Adam Pauls, Dan Klein
IBERAMIA
2010
Springer
15 years 2 months ago
Text-to-Text Surface Realisation Using Dependency-Tree Replacement
Surface realisation - the task of producing word strings from non-linguistic input data - has been the focus of a great deal of research in the field of data-to-text Natural Langu...
Eder Miranda de Novais, Thiago Dias Tadeu, Ivandr&...
162
Voted
EMNLP
2011
14 years 3 months ago
Learning Sentential Paraphrases from Bilingual Parallel Corpora for Text-to-Text Generation
Previous work has shown that high quality phrasal paraphrases can be extracted from bilingual parallel corpora. However, it is not clear whether bitexts are an appropriate resourc...
Juri Ganitkevitch, Chris Callison-Burch, Courtney ...
126
Voted
ACL
2008
15 years 5 months ago
Trainable Generation of Big-Five Personality Styles through Data-Driven Parameter Estimation
Previous work on statistical language generation has primarily focused on grammaticality and naturalness, scoring generation possibilities according to a language model or user fe...
François Mairesse, Marilyn A. Walker
127
Voted
ECML
2003
Springer
15 years 8 months ago
A Generative Model for Semantic Role Labeling
Determining the semantic role of sentence constituents is a key task in determining sentence meanings lying behind a veneer of variant syntactic expression. We present a model of n...
Cynthia A. Thompson, Roger Levy, Christopher D. Ma...