158 search results - page 12 / 32 » emnlp 2009 |
EMNLP
2009
14 years 8 months ago
2009
Randomised techniques allow very big language models to be represented succinctly. However, being batch-based they are unsuitable for modelling an unbounded stream of language whi...
EMNLP
2009
14 years 8 months ago
2009
We investigate the effectiveness of selftraining PCFG grammars with latent annotations (PCFG-LA) for parsing languages with different amounts of labeled training data. Compared to...
EMNLP
2009
14 years 8 months ago
2009
We present the first unsupervised approach to the problem of learning a semantic parser, using Markov logic. Our USP system transforms dependency trees into quasi-logical forms, r...
131
click to vote
EMNLP
2009
14 years 8 months ago
2009
Distinguishing speculative statements from factual ones is important for most biomedical text mining applications. We introduce an approach which is based on solving two sub-probl...
EMNLP
2009
14 years 8 months ago
2009
Machine involvement has the potential to speed up language documentation. We assess this potential with timed annotation experiments that consider annotator expertise, example sel...