70 search results - page 6 / 14 » Using sentence connectors for evaluating MT output |
NAACL
2007
14 years 10 months ago
2007
The quality of a sentence translated by a machine translation (MT) system is difficult to evaluate. We propose a method for automatically evaluating the quality of each translati...
ACL
2001
14 years 10 months ago
2001
We present a machine learning approach to evaluating the wellformedness of output of a machine translation system, using classifiers that learn to distinguish human reference tran...
100
click to vote
MT
2002
14 years 9 months ago
2002
We present MARS (Multilingual Automatic tRanslation System), a research prototype speech-to-speech translation system. MARS is aimed at two-way conversational spoken language trans...
ACL
2006
14 years 10 months ago
2006
Japanese case markers, which indicate the grammatical relation of the complement NP to the predicate, often pose challenges to the generation of Japanese text, be it done by a for...
ACL
2012
12 years 11 months ago
2012
This paper presents a two-step approach to compress spontaneous spoken utterances. In the first step, we use a sequence labeling method to determine if a word in the utterance ca...