Sciweavers

10 search results - page 2 / 2
» Corpus Aligner (CorAl) Evaluation on English-Croatian Parall...
Sort
View
LREC
2008
90views Education» more  LREC 2008»
13 years 8 months ago
Word Alignment Annotation in a Japanese-Chinese Parallel Corpus
Parallel corpora are critical resources for machine translation research and development since parallel corpora contain translation equivalences of various granularities. Manual a...
Yujie Zhang, Zhulong Wang, Kiyotaka Uchimoto, Qing...
AIRS
2004
Springer
14 years 10 days ago
Multilingual Relevant Sentence Detection Using Reference Corpus
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...
Ming-Hung Hsu, Ming-Feng Tsai, Hsin-Hsi Chen
ACL
2010
13 years 5 months ago
Bilingual Lexicon Generation Using Non-Aligned Signatures
Bilingual lexicons are fundamental resources. Modern automated lexicon generation methods usually require parallel corpora, which are not available for most language pairs. Lexico...
Daphna Shezaf, Ari Rappoport
LREC
2010
159views Education» more  LREC 2010»
13 years 8 months ago
Bilingual Lexicon Induction: Effortless Evaluation of Word Alignment Tools and Production of Resources for Improbable Language P
In this paper, we present a simple protocol to evaluate word aligners on bilingual lexicon induction tasks from parallel corpora. Rather than resorting to gold standards, it relie...
Adrien Lardilleux, Julien Gosme, Yves Lepage
ACL
1998
13 years 8 months ago
Bitext Correspondences through Rich Mark-up
Rich mark-up can considerably benefit the process of establishing bitext correspondences, that is, the task of providing correct identification and alignment methods for text segm...
Raquel Martínez, Joseba Abaitua, Arantza Ca...