35 search results - page 1 / 7 » Learning Bigrams from Unigrams |
52
Voted
ACL
2008
14 years 11 months ago
2008
Traditional wisdom holds that once documents are turned into bag-of-words (unigram count) vectors, word orders are completely lost. We introduce an approach that, perhaps surprisi...
NIPS
2008
14 years 11 months ago
2008
We present a correlated bigram LSA approach for unsupervised LM adaptation for automatic speech recognition. The model is trained using efficient variational EM and smoothed using...
TREC
2003
14 years 11 months ago
2003
In the biological domain, to extract the newly discovered functional features from massive literature is a major challenging issue. To automatically annotate GeneRIF in a new lite...
73
Voted
ACL
2006
14 years 11 months ago
2006
Developing better methods for segmenting continuous text into words is important for improving the processing of Asian languages, and may shed light on how humans learn to segment...
ICML
2006
IEEE
15 years 10 months ago
2006
IEEE
Some models of textual corpora employ text generation methods involving n-gram statistics, while others use latent topic variables inferred using the "bag-of-words" assu...