Apertium: a free/open-source platform for rule-based machine translation

Forcada, Mikel L.; Ginestí-Rosell, Mireia; Nordfalk, Jacob; O'Regan, Jim; Ortiz-Rojas, Sergio; Pérez-Ortiz, Juan Antonio; Sánchez-Martínez, Felipe; Ramírez-Sánchez, Gema; Tyers, Francis M.

doi:10.1007/s10590-011-9090-0

Cited by 177 publications

(159 citation statements)

References 16 publications

Supporting

Mentioning

141

Contrasting

Unclassified

Order By: Relevance

“…For actual morphological analysis, we use the lttoolbox formalism, a morphological analysis framework used within the open-source machine translation framework, Apertium (Forcada et al, 2011). There exists an lttoolbox-based morphological analyser for Marathi 2 , with a coverage of 80% on the Marathi Wikipedia.…”

Section: Lttoolboxmentioning

confidence: 99%

Finite-State Back-Transliteration for Marathi

Ravishankar

2017

The Prague Bulletin of Mathematical Linguistics

View full text Add to dashboard Cite

show abstract

Section: Lttoolboxmentioning

confidence: 99%

Finite-State Back-Transliteration for Marathi

Ravishankar

2017

The Prague Bulletin of Mathematical Linguistics

View full text Add to dashboard Cite

show abstract

“…The parallel corpora exploited for all the language pairs include: Common Crawl mined from the public web crawl hosted on Amazon's Elastic Cloud [59], EuroParl version 6 extracted from the proceedings of the EU Parliament [11], JRC-Acquis Multilingual Parallel Corpus version 3.0 extracted from Acquis Communautaire, the total body of European Union law [13], the News Commentary corpus of news analysis from the Project Syndicate [14], and the OJEU corpus with texts from the Official Journal of the European Union including legislation documents, information notices, and public procurements, made available by the Apertium project [60]. We also make use of the dictionary data extracted from DBpedia and not identified as medical-domain, see Section 2.2.1.…”

Section: General-domain Parallel Datamentioning

confidence: 99%

Adaptation of machine translation for multilingual information retrieval in the medical domain

Pecina¹,

Dušek²,

Goeuriot³

et al. 2014

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

Objective. We investigate machine translation (MT) of user search queries in the context of cross-lingual information retrieval (IR) in the medical domain. The main focus is on techniques to adapt MT to increase translation quality; however, we also explore MT adaptation to improve effectiveness of cross-lingual IR.Methods and Data. Our MT system is Moses, a state-of-the-art phrase-based statistical machine translation system. The IR system is based on the BM25 retrieval model implemented in the Lucene search engine. The MT techniques employed in this work include in-domain training and tuning, intelligent training data selection, optimization of phrase table configuration, compound splitting, and exploiting synonyms as translation variants. The IR methods include morphological normalization and using multiple translation variants for query expansion. The experiments are performed and thoroughly evaluated on three language pairs: Czech-English, German-English, and French-English. MT quality is evaluated on data sets created within the Khresmoi project and IR effectiveness is tested on the CLEF eHealth 2013 data sets.Results. The search query translation results achieved in our experiments are outstanding -our systems outperform not only our strong baselines, but also Google Translate and Microsoft Bing Translator in direct comparison carried out on all the language pairs. The baseline BLEU scores increased from 26.59 to 41.45 for Czech-English, from 23.03 to 40.82 for German-English, and from 32.67 to 40.82 for French-English. This is a 55% improvement on average. In terms of the IR performance on this particular test collection, a significant improvement over the baseline is achieved only for French-English. For Czech-English and German-English, the increased MT quality does not lead to better IR results.Conclusions. Most of the MT techniques employed in our experiments improve MT of medical search queries. Especially the intelligent training data selection proves to be very successful for domain adaptation of MT. Certain improvements are also obtained from German compound splitting on the source language side. Translation quality, however, does not appear to correlate with the IR performance -better translation does not necessarily yield better retrieval. We discuss in detail the contribution of the individual techniques and state-of-the-art features and provide future research directions.

show abstract

“…The words originating from other languages (less than 0.1%, and principally Latin) are labelled solely with their language. The part-of-speech categories and their tags -shown in Table 1 together with their relative frequencies-are based on those defined by the Apertium machine translation platform (Forcada et al, 2011) for the dictionaries in the Spanish-Catalan language pair since, to the best of our knowledge, there is no Spanish diachronic lexicon available in digital form under a free/open-source license. Having a lexicon in digital form facilitated the manual annotation of the corpus as described below.…”

Section: Corpus Descriptionmentioning

confidence: 99%

An open diachronic corpus of historical Spanish

Sánchez-Martínez

Martínez-Sempere

Ivars-Ribes

et al. 2013

Lang Resources & Evaluation

Self Cite

View full text Add to dashboard Cite

The impact-es diachronic corpus of historical Spanish compiles over one hundred books -containing approximately 8 million words-in addition to a complementary lexicon which links more than 10 thousand lemmas with attestations of the different variants found in the documents. This textual corpus and the accompanying lexicon have been released under an open license (Creative Commons by-nc-sa) in order to permit their intensive exploitation in linguistic research.Approximately 7% of the words in the corpus (a selection aimed at enhancing the coverage of the most frequent word forms) have been annotated with their lemma, part of speech, and modern equivalent. This paper describes the annotation criteria followed and the standards, based on the Text Encoding Initiative recommendations, used to represent the texts in digital form.

show abstract

Apertium: a free/open-source platform for rule-based machine translation

Cited by 177 publications

References 16 publications

Finite-State Back-Transliteration for Marathi

Finite-State Back-Transliteration for Marathi

Adaptation of machine translation for multilingual information retrieval in the medical domain

An open diachronic corpus of historical Spanish

Contact Info

Product

Resources

About