118 search results - page 7 / 24 » emnlp 2008 |
EMNLP
2008
14 years 11 months ago
2008
In domains with insufficient matched training data, language models are often constructed by interpolating component models trained from partially matched corpora. Since the ngram...
116
click to vote
EMNLP
2008
14 years 11 months ago
2008
One major bottleneck in conversational systems is their incapability in interpreting unexpected user language inputs such as out-ofvocabulary words. To overcome this problem, conv...
EMNLP
2008
14 years 11 months ago
2008
Compared to the telephone, email based customer care is increasingly becoming the preferred channel of communication for corporations and customers. Most email-based customer care...
EMNLP
2008
14 years 11 months ago
2008
Parallel web pages are important source of training data for statistical machine translation. In this paper, we present a new approach to sentence alignment on parallel web pages....
EMNLP
2008
14 years 11 months ago
2008
The graph-based ranking algorithm has been recently exploited for multi-document summarization by making only use of the sentence-to-sentence relationships in the documents, under...