An Approach to Acquire Word Translations from Non-parallel Texts

Gamallo, Pablo; Campos, José Ramom Pichel

doi:10.1007/11595014_59

Cited by 6 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some researchers [9,10] have described methods for learning word translations from the article-level-aligned corpus. Otero and Campos [11] proposed an approach to extract word translations. Their approach depends on bilingual pairs for lexico-syntactic templates that are previously extracted from parallel corpora.…”

Section: Related Workmentioning

confidence: 99%

Study on Unknown Term Translation Mining from Google Snippets

Yao

2019

Information

View full text Add to dashboard Cite

Bilingual web pages are widely used to mine translations of unknown terms. This study focused on an effective solution for obtaining relevant web pages, extracting translations with correct lexical boundaries, and ranking the translation candidates. This research adopted co-occurrence information to obtain the subject terms and then expanded the source query with the translation of the subject terms to collect effective bilingual search engine snippets. Afterwards, valid candidates were extracted from small-sized, noisy bilingual corpora using an improved frequency change measurement that combines adjacent information. This research developed a method that considers surface patterns, frequency–distance, and phonetic features to elect an appropriate translation. The experimental results revealed that the proposed method performed remarkably well for mining translations of unknown terms.

show abstract

Section: Related Workmentioning

confidence: 99%

Study on Unknown Term Translation Mining from Google Snippets

Yao

2019

Information

View full text Add to dashboard Cite

show abstract

“…Once context vectors have been built for all the words in both languages, the similarity between a source word's context vector and all the context vectors in the target language is computed. The most typical similarity measures are cosine (Fung 1998), Jaccard (Otero and Campos 2005) and Dice (Otero 2007).…”

Section: Extraction Of Translation Equivalentsmentioning

confidence: 99%

Najboljši ali lažni prijatelji? Luščenje slovensko-hrvaških prevodnih ustreznic in lažnih prijateljev iz korpusov

Fišer

Ljubešić

2013

SLO2.0

View full text Add to dashboard Cite

V prispevku predstavimo korpusni pristop k samodejnemu luščenju prevodnih ustreznic in lažnih prijateljev med slovenščino in hrvaščino. Pristop izkorišča ortografske podobnosti med jezikoma in temelji na predpostavki distribucijske semantike, ki se glasi, da govorci obeh jezikov besede s podobnim pomenom uporabljamo v podobnih kontekstih. To nam po eni strani omogoča hitro izgradnjo slovensko-hrvaškega dvojezičnega leksikona, za katero razen primerljivih spletnih korpusov ne potrebujemo nobenega drugega vira znanja. Po drugi strani pa lahko na podlagi iste predpostavke s pomočjo korpusnih podatkov prepoznamo tiste sorodnice, ki so si podobne zgolj površinsko, leksikalizirajo pa različne pojme in se zato tudi različno uporabljajo. Predstavljen pristop je jezikovno neodvisen, zaradi česar je privlačen za številna področja računalniške obdelave naravnega jezika, kjer še vedno vlada veliko pomanjkanje leksikalnih virov, njihove ročne izdelave pa si ne moremo privoščiti. Pristop je prav tako zelo koristen v leksikografiji in za poučevanje tujih jezikov, saj nam pomaga osvetliti leksikalne posebnosti za določen jezikovni par oziroma strokovno področje.

show abstract

“…Otero and Campos (2005) extract English-Spanish pairs of lexico-syntactic patterns from a small parallel corpus. They then construct context vectors for all English and Spanish words by recording their frequency of occurrence in each of these patterns.…”

Section: Related Work On Cross-lingual Lexical Acquisitionmentioning

confidence: 99%

A graph-theoretic algorithm for automatic extension of translation lexicons

Dorow

Laws

Michelbacher

et al. 2009

Proceedings of the Workshop on Geometrical Models of Natural Language Semantics - GEMS '09

View full text Add to dashboard Cite

This paper presents a graph-theoretic approach to the identification of yetunknown word translations. The proposed algorithm is based on the recursive Sim-Rank algorithm and relies on the intuition that two words are similar if they establish similar grammatical relationships with similar other words. We also present a formulation of SimRank in matrix form and extensions for edge weights, edge labels and multiple graphs.

show abstract

An Approach to Acquire Word Translations from Non-parallel Texts

Cited by 6 publications

References 12 publications

Study on Unknown Term Translation Mining from Google Snippets

Study on Unknown Term Translation Mining from Google Snippets

Najboljši ali lažni prijatelji? Luščenje slovensko-hrvaških prevodnih ustreznic in lažnih prijateljev iz korpusov

A graph-theoretic algorithm for automatic extension of translation lexicons

Contact Info

Product

Resources

About