Extracting word correspondences from bilingual corpora based on word co-occurrences information

Kaji, Hiroyuki; Aizono, Toshiko

doi:10.3115/992628.992636

Cited by 28 publications

(18 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Sadat et al (2003) automatically extracted bilingual word pairs from comparable corpora. Others have leveraged parallel corpora or bilingual dictionaries for lexical acquisition (Echizen-ya et al 2006;Kaji and Aizono 1996;Rapp 1999;Tanaka and Iwasaki, 1996). However, our work deals with the fundamentally different task of translating a large thesaurus, where one can leverage the structural properties of the resource.…”

Section: Related Workmentioning

confidence: 99%

A cost-effective lexical acquisition process for large-scale thesaurus translation

Lin

Murray

Dorr

et al. 2008

Lang Resources & Evaluation

View full text Add to dashboard Cite

Thesauri and controlled vocabularies facilitate access to digital collections by explicitly representing the underlying principles of organization. Translation of such resources into multiple languages is an important component for providing multilingual access. However, the specificity of vocabulary terms in most thesauri precludes fully-automatic translation using general-domain lexical resources. In this paper, we present an efficient process for leveraging human translations to construct domain-specific lexical resources. This process is illustrated on a thesaurus of 56,000 concepts used to catalog a large archive of oral histories. We elicited human translations on a small subset of concepts, induced a probabilistic phrase dictionary from these translations, and used the resulting resource to automatically translate the rest of the thesaurus. Two separate evaluations demonstrate the acceptability of the automatic translations and the cost-effectiveness of our approach.

show abstract

Section: Related Workmentioning

confidence: 99%

A cost-effective lexical acquisition process for large-scale thesaurus translation

Lin

Murray

Dorr

et al. 2008

Lang Resources & Evaluation

View full text Add to dashboard Cite

show abstract

“…Among previous studies, one [6] uses the co-occurrence of words depending on the number of co-occurrence words and their frequency. Such a method is insufficient in terms of efficient extraction of bilingual word pairs.…”

Section: Experiments and Discussionmentioning

confidence: 99%

Learning Method for Automatic Acquisition of Translation Knowledge

Echizen-ya

Araki

Momouchi

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper presents a new learning method for automatic acquisition of translation knowledge from parallel corpora. We apply this learning method to automatic extraction of bilingual word pairs from parallel corpora. In general, similarity measures are used to extract bilingual word pairs from parallel corpora. However, similarity measures are insufficient because of the sparse data problem. The essence of our learning method is this presumption: in local parts of bilingual sentence pairs, the equivalents of words that adjoin the source language words of bilingual word pairs also adjoin the target language words of bilingual word pairs. Such adjacent information is acquired automatically in our method. We applied our method to systems based on various similarity measures, thereby confirming the effectiveness of our method.

show abstract

“…For Cosine, the association values of two words with the same context are joined using their product, while for JaccardMin (Grefenstette 1994;Kaji and Aizono 1996) and DiceMin (Curran et al 2002;van der Plas and Bouma 2004;Gamallo 2007) only the smallest association weight is considered. For the Lin coefficient, the association values of common contexts are summed (Lin 1998), where c j [ C 1,2 if and only if A(w 1 , c j ) > 0 and A(w 2 , c j ) > 0.…”

Section: Ten Similarity Measuresmentioning

confidence: 99%

Is singular value decomposition useful for word similarity extraction?

Gamallo

Bordag

2010

Lang Resources & Evaluation

View full text Add to dashboard Cite

In this paper, we analyze the behaviour of Singular Value Decomposition in a number of word similarity extraction tasks, namely acquisition of translation equivalents from comparable corpora. Special attention is paid to two different aspects: computational efficiency and extraction quality. The main objective of the paper is to describe several experiments comparing methods based on Singular Value Decomposition (SVD) to other strategies. The results lead us to conclude that SVD makes the extraction less computationally efficient and much less precise than other more basic models for the task of extracting translation equivalents from comparable corpora.

show abstract

Extracting word correspondences from bilingual corpora based on word co-occurrences information

Cited by 28 publications

References 8 publications

A cost-effective lexical acquisition process for large-scale thesaurus translation

A cost-effective lexical acquisition process for large-scale thesaurus translation

Learning Method for Automatic Acquisition of Translation Knowledge

Is singular value decomposition useful for word similarity extraction?

Contact Info

Product

Resources

About