967 search results - page 10 / 194 » Topical Word Embeddings |
EMNLP
2010
13 years 5 months ago
2010
Existing graph-based ranking methods for keyphrase extraction compute a single importance score for each word via a single random walk. Motivated by the fact that both documents a...
WIAMIS
2009
IEEE
14 years 2 months ago
2009
IEEE
This paper suggests an alternative solution for the task of spoken document retrieval (SDR). The proposed system runs retrieval on multi-level transcriptions (word and phone) prod...
EMNLP
2008
13 years 9 months ago
2008
Previously topic models such as PLSI (Probabilistic Latent Semantic Indexing) and LDA (Latent Dirichlet Allocation) were developed for modeling the contents of plain texts. Recent...
ICML
2007
IEEE
14 years 8 months ago
2007
IEEE
The four-level pachinko allocation model (PAM) (Li & McCallum, 2006) represents correlations among topics using a DAG structure. It does not, however, represent a nested hiera...
ACL
2008
13 years 9 months ago
2008
We present the development and tuning of a topic-adapted language model for word prediction, which improves keystroke savings over a comparable baseline. We outline our plans to d...