A Comparison of Methods for Identifying the Translation of Words in a Comparable Corpus: Recipes and Limits
Fuente:
Redalyc
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Artículo científico |
| Lenguaje: | en |
| Publicado: |
Instituto Politécnico Nacional
2016
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1876470587519401984 |
|---|---|
| author | Laurent Jakubina |
| author_facet | Laurent Jakubina |
| contents | A Comparison of Methods for Identifying the Translation of Words in a Comparable Corpus: Recipes and Limits Laurent Jakubina Philippe Langlais Computación Comparable corpora rare word translation distributional approaches bilingual lexicon induction Identifying translations in comparable corpora is a challenge that has attracted many researchers since a long time. It has applications in several applications including Machine Translation and Cross-lingual Information Retrieval. In this study we compare three state-of-the-art approaches for these tasks: the so-called context-based projection method, the projection of monolingual word embeddings, as well as a method dedicated to identify translations of rare words. We carefully explore the hyper-parameters of each method and measure their impact on the task of identifying the translation of English words in Wikipedia into French. Contrary to the standard practice, we designed a test case where we do not resort to heuristics in order to pre-select the target vocabulary among which to find translations, therefore pushing each method to its limit. We show that all the approaches we tested have a clear bias toward frequent words. In fact, the best approach we tested could identify the translation of a third of a set of frequent test words, while it could only translate around 10% of rare words. 2016 artículo científico 1405-5546 https://www.redalyc.org/articulo.oa?id=61547469013 en http://www.redalyc.org/revista.oa?id=615 Computación y Sistemas application/pdf Instituto Politécnico Nacional Computación y Sistemas (México) Num.3 Vol.20 |
| format | Artículo científico |
| id | redalyc_61547469013 |
| institution | Redalyc |
| language | en |
| publishDate | 2016 |
| publisher | Instituto Politécnico Nacional |
| spellingShingle | A Comparison of Methods for Identifying the Translation of Words in a Comparable Corpus: Recipes and Limits Laurent Jakubina Computación Comparable corpora rare word translation distributional approaches bilingual lexicon induction A Comparison of Methods for Identifying the Translation of Words in a Comparable Corpus: Recipes and Limits Laurent Jakubina Philippe Langlais Computación Comparable corpora rare word translation distributional approaches bilingual lexicon induction Identifying translations in comparable corpora is a challenge that has attracted many researchers since a long time. It has applications in several applications including Machine Translation and Cross-lingual Information Retrieval. In this study we compare three state-of-the-art approaches for these tasks: the so-called context-based projection method, the projection of monolingual word embeddings, as well as a method dedicated to identify translations of rare words. We carefully explore the hyper-parameters of each method and measure their impact on the task of identifying the translation of English words in Wikipedia into French. Contrary to the standard practice, we designed a test case where we do not resort to heuristics in order to pre-select the target vocabulary among which to find translations, therefore pushing each method to its limit. We show that all the approaches we tested have a clear bias toward frequent words. In fact, the best approach we tested could identify the translation of a third of a set of frequent test words, while it could only translate around 10% of rare words. 2016 artículo científico 1405-5546 https://www.redalyc.org/articulo.oa?id=61547469013 en http://www.redalyc.org/revista.oa?id=615 Computación y Sistemas application/pdf Instituto Politécnico Nacional Computación y Sistemas (México) Num.3 Vol.20 |
| title | A Comparison of Methods for Identifying the Translation of Words in a Comparable Corpus: Recipes and Limits |
| topic | Computación Comparable corpora rare word translation distributional approaches bilingual lexicon induction |
| url | https://www.redalyc.org/articulo.oa?id=61547469013 |