Deep linguistic multilingual translation and bilingual dictionaries

Wehrli, Eric; Nerima, Luka; Scherrer, Yves

doi:10.3115/1626431.1626450

Cited by 18 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Another interesting example can be found for the WMT09 French-English translation task of News data: among twenty participants, the output generated by the Google system 6 has the best BLEU score as well as the best human sentence ranking score (Callison-Burch et al 2007), whereas the scores for the translation produced by University of Geneva (Wehrli, Nerima, and Scherrer 2009) are the lowest. The sentence rank of a translation system is defined as percentage of sentences for which this system is judged by human evaluators to be better or equal than any other system.…”

Section: Different Translation Systemsmentioning

confidence: 99%

Towards Automatic Error Analysis of Machine Translation Output

Popović

Ney

2011

Computational Linguistics

View full text Add to dashboard Cite

Evaluation and error analysis of machine translation output are important but difficult tasks. In this article, we propose a framework for automatic error analysis and classification based on the identification of actual erroneous words using the algorithms for computation of Word Error Rate (WER) and Position independent word Error Rate (PER) which is just a very first step towards development of automatic evaluation measures which provide more specific information of certain translation problems. The proposed approach enables the use of various types of linguistic knowledge in order to classify translation errors in many different ways. This work focuses on one possible set-up, namely on five error categories: inflectional errors, errors due to wrong word order, missing words, extra words and incorrect lexical choices. For each of the categories, we analyse the contribution of various POS classes. We compared the results of automatic error analysis with the results of human error analysis in order to investigate two possible applications: estimating the contribution of each error type in a given translation output in order to identify the main sources of errors for a given translation system, and comparing different translation outputs using the introduced error categories in order to obtain more information about advantages and disadvantages of different systems and possibilites for improvements, as well as about advantages and disadvantages of applied methods for improvements. We used Arabic-English Newswire and Broadcast News and Chinese-English Newswire outputs created in the framework of the GALE project, several Spanish and English European Parliament outputs generated during the TC-Star project, and three German-English outputs generated in the framework of the fourth Machine Translation Workshop (WMT). We show that our results correlate very well with the results of a human error analysis, and that all our metrics except the extra words reflect well the differences between different versions of the same translation system as well as the differences between different translation systems.

show abstract

Section: Different Translation Systemsmentioning

confidence: 99%

Towards Automatic Error Analysis of Machine Translation Output

Popović

Ney

2011

Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…Existem numerosos trabalhos sobre construção automática de novos léxicos bilíngues a partir dos já existentes (Paik et al, 2004;Ahn & Frampton, 2006;Zhang, Ma & Isahara, 2007;Nerima & Wehrli, 2008;Kaji et al, 2008;Simões & Guinovart, 2010;Wehrli et al, 2009).…”

Section: Trabalho Relacionadounclassified

Uso de corpora comparáveis para filtrar dicionários bilíngues gerados por transitividade

Gamallo¹

2014

DELTA

View full text Add to dashboard Cite

Este artigo propõe um método para a construção de novos dicionários bilíngues a partir de dicionários já existentes e da exploração de corpora comparáveis. Mais concretamente, um novo dicionário para um par de línguas é gerado em duas etapas: primeiro, cruzam-se dicionários bilíngues entre essas línguas e uma terceira intermediária e, segundo, o resultado do cruzamento, que contém um número elevado de traduções espúrias causadas pela ambiguidade das palavras da língua intermediária, filtra-se com apoio em textos de temática comparável nas duas línguas alvo. A qualidade do dicionário derivado é muito alta, próxima dos dicionários construídos manualmente. Descreveremos um caso de estudo onde criaremos um novo dicionário Inglês-Português com mais de 7.000 entradas bilíngues geradas pelo nosso método.

show abstract

“…In our own work, we assessed the impact of collocational knowledge on a rule-based translation system, namely, the Its-2 system [54] based on the Fips parser (cf. Section 2).…”

Section: Exploiting Collocations In Machine Translationmentioning

confidence: 99%

“…We experimented with and without dictionary information (in our case, the lexical databases of the Its-2 in-house machine translation system[54]). …”

mentioning

confidence: 99%

On Collocations and Their Interaction with Parsing and Translation

Seretan

2013

Informatics

View full text Add to dashboard Cite

We address the problem of automatically processing collocations—a subclass of multi-word expressions characterized by a high degree of morphosyntactic ﬂexibility—in the context of two major applications, namely, syntactic parsing and machine translation. We show that parsing and collocation identiﬁcation are processes that are interrelated and that beneﬁt from each other, inasmuch as syntactic information is crucial for acquiring collocations from corpora and, vice versa, collocational information can be used to improve parsing performance. Similarly, we focus on the interrelation between collocations and machine translation, highlighting the use of translation information for multilingual collocation identiﬁcation, as well as the use of collocational knowledge for improving translation. We give a panorama of the existing relevant work, and we parallel the literature surveys with our own experiments involving a symbolic parser and a rule-based translation system. The results show a signiﬁcant improvement over approaches in which the corresponding tasks are decoupled

show abstract

Deep linguistic multilingual translation and bilingual dictionaries

Cited by 18 publications

References 8 publications

Towards Automatic Error Analysis of Machine Translation Output

Towards Automatic Error Analysis of Machine Translation Output

Uso de corpora comparáveis para filtrar dicionários bilíngues gerados por transitividade

On Collocations and Their Interaction with Parsing and Translation

Contact Info

Product

Resources

About