66 search results - page 6 / 14 » Evolving natural language grammars without supervision |
EMNLP
2009
14 years 7 months ago
2009
This paper presents a new approach to selecting the initial seed set using stratified sampling strategy in bootstrapping-based semi-supervised learning for semantic relation class...
132
click to vote
EMNLP
2011
13 years 9 months ago
2011
We introduce a novel machine learning framework based on recursive autoencoders for sentence-level prediction of sentiment label distributions. Our method learns vector space repr...
EMNLP
2009
14 years 7 months ago
2009
Tree Adjoining Grammars have well-known advantages, but are typically considered too difficult for practical systems. We demonstrate that, when done right, adjoining improves tran...
LATA
2010
Springer
15 years 4 months ago
2010
Springer
We extend stochastic context-free grammars such that the probability of applying a production can depend on the length of the subword that is generated from the application and sho...
CICLING
2003
Springer
15 years 2 months ago
2003
Springer
Abstract. This paper reports on the development of a finite state system for finding grammar errors without actually specifying the error. A corpus of Swedish text written by chi...