Sciweavers

116 search results - page 14 / 24
» Extraction of Lexical Translations from Non-Aligned Corpora
Sort
View
NAACL
2003
13 years 9 months ago
Syntax-based Alignment of Multiple Translations: Extracting Paraphrases and Generating New Sentences
We describe a syntax-based algorithm that automatically builds Finite State Automata (word lattices) from semantically equivalent translation sets. These FSAs are good representat...
Bo Pang, Kevin Knight, Daniel Marcu
LREC
2008
159views Education» more  LREC 2008»
13 years 9 months ago
Automatic Construction of a Japanese-Chinese Dictionary via English
This paper proposes a method of constructing a dictionary for a pair of languages from bilingual dictionaries between each of the languages and a third language. Such a method wou...
Hiroyuki Kaji, Shin'ichi Tamamura, Dashtseren Erde...
SEMCO
2009
IEEE
14 years 2 months ago
LexPar: A Freely Available English Paraphrase Lexicon Automatically Extracted from FrameNet
—This is a paper about a new resource, namely an English paraphrase dictionary extracted from the FrameNet lexicon and its example data base. I. THE LEXPAR PARAPHRASE DICTIONARY ...
Bob Coyne, Owen Rambow
SIGIR
1998
ACM
13 years 11 months ago
Automatic Acquisition of Phrasal Knowledge for English-Chinese Bilingual Information Retrieval
Extraction of phrasal knowledge, such as proper names, domain-specific keyphrases and lexical templates from a domain-specific text collection are significant for developing effec...
Ming-Jer Lee, Lee-Feng Chien
LREC
2008
153views Education» more  LREC 2008»
13 years 9 months ago
Building a Multilingual Lexical Resource for Named Entity Disambiguation, Translation and Transliteration
In this paper, we present HeiNER, the multilingual Heidelberg Named Entity Resource. HeiNER contains 1,547,586 disambiguated English Named Entities together with translations and ...
Wolodja Wentland, Johannes Knopp, Carina Silberer,...