29 search results - page 5 / 6 » Experiments on Processing Overlapping Parallel Corpora |
LREC
2008
14 years 11 months ago
2008
In current phrase-based Statistical Machine Translation systems, more training data is generally better than less. However, a larger data set eventually introduces a larger model ...
TASLP
2008
14 years 9 months ago
2008
Abstract--This paper is concerned with the automatic recognition of dialogue acts (DAs) in multiparty conversational speech. We present a joint generative model for DA recognition ...
AIRS
2004
Springer
15 years 3 months ago
2004
Springer
IR with reference corpus is one approach when dealing with relevant sentences detection, which takes the result of IR as the representation of query (sentence). Lack of informatio...
WWW
2005
ACM
15 years 10 months ago
2005
ACM
We consider the problem of indexing high-dimensional data for answering (approximate) similarity-search queries. Similarity indexes prove to be important in a wide variety of sett...
107
click to vote
ICPP
1999
IEEE
15 years 1 months ago
1999
IEEE
The probability of failures in software distributed shared memory (SDSM) increases as the system size grows. This paper introduces a new, efficient message logging technique, call...