Rule-Based Machine Translation for the Italian–Sardinian Language Pair

Tyers, Francis M.; Font, Hèctor Alòs i; Fronteddu, Gianfranco; Martín-Mor, Adrià

doi:10.1515/pralin-2017-0022

Cited by 3 publications

(12 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We gathered data from e-commence page, Cachitos de Plata, details in Section 2. 3. Statistics of these corpora are provided in Table 6.…”

Section: Real Scenario Resultsmentioning

confidence: 99%

“…For this reason, RBMT systems are loosing weight in the state of the art in comparison to more robust and cost-effective approaches, such as statistical machine translation. Nevertheless, they are still in use in some commercial systems, such as Apertium [2,3] and GramTrans [4].…”

Section: Machine Translationmentioning

confidence: 99%

“…Direct translation probability, which is similar to the inverse translation probability computed in the reverse translation direction. 3. Direct and inverse lexical translation probabilities.…”

Section: The Different Features H M (•mentioning

confidence: 99%

“…This corpus has been obtained for the Information Technology (IT) adaptation 3 The IT translation task is focused on domain adaptation of MT to the information technology domain and translation of answers in a crosslingual help-desk service. Hardware and software troubleshooting answers are translated from English to the user's languages: Bulgarian, Czech, German, Spanish, Basque, Dutch and Portuguese.…”

Section: Information Technology Corpusmentioning

confidence: 99%

“…In the previous Section 3. 3.1.1, we exposed that the size of the training corpus and the domain has an important impact in the final translation quality [121]. In these circumstances, specialised domain adaptation techniques are required to effectively utilise the available out-ofdomain parallel data to improve in-domain translation quality.…”

Section: Data Selectionmentioning

confidence: 99%

See 4 more Smart Citations

Advanced techniques for domain adaptation in Statistical Machine Translation

Rios¹

View full text Add to dashboard Cite

Machine translation is a sub-field of Natural Language Processing and Artificial Intelligence that investigates the use of computers to translate a given text from one human language to another. More specifically, Statistical Machine Translation is an approach used to build these translation systems. The quality of these systems depends mostly, on the example translations used to train or adapt the models. Corpora can come from a variety of sources, many of which are not optimal for common specific domains. Hence, the primary purpose of this thesis is to find out the right data to train or adapt models from, applied to a particular domain or task. This thesis proposes different Data Selection methods to identify task-relevant translation training data from a general data pool.

show abstract

“…We gathered data from e-commence page, Cachitos de Plata, details in Section 2. 3. Statistics of these corpora are provided in Table 6.…”

Section: Real Scenario Resultsmentioning

confidence: 99%

Section: Machine Translationmentioning

confidence: 99%

Section: The Different Features H M (•mentioning

confidence: 99%

Section: Information Technology Corpusmentioning

confidence: 99%

Section: Data Selectionmentioning

confidence: 99%

See 3 more Smart Citations

Advanced techniques for domain adaptation in Statistical Machine Translation

Rios¹

View full text Add to dashboard Cite

show abstract

Recent advances in Apertium, a free/open-source rule-based machine translation platform for low-resource languages

Khanna

Washington

Tyers

et al. 2021

Machine Translation

Self Cite

View full text Add to dashboard Cite

This paper presents an overview of Apertium, a free and open-source rule-based machine translation platform. Translation in Apertium happens through a pipeline of modular tools, and the platform continues to be improved as more language pairs are added. Several advances have been implemented since the last publication, including some new optional modules: a module that allows rules to process recursive structures at the structural transfer stage, a module that deals with contiguous and discontiguous multi-word expressions, and a module that resolves anaphora to aid translation. Also highlighted is the hybridisation of Apertium through statistical modules that augment the pipeline, and statistical methods that augment existing modules. This includes morphological disambiguation, weighted structural transfer, and lexical selection modules that learn from limited data. The paper also discusses how a platform like Apertium can be a critical part of access to language technology for so-called low-resource languages, which might be ignored or deemed unapproachable by popular corpus-based translation technologies. Finally, the paper presents some of the released and unreleased language pairs, concluding with a brief look at some supplementary Apertium tools that prove valuable to users as well as language developers. All Apertium-related code, including language data, is free/open-source and available at https://github.com/apertium.

show abstract

Language Varieties of Italy: Technology Challenges and Opportunities

Ramponi

2024

Transactions of the Association for Computational Linguistics

View full text Add to dashboard Cite

Italy is characterized by a one-of-a-kind linguistic diversity landscape in Europe, which implicitly encodes local knowledge, cultural traditions, artistic expressions, and history of its speakers. However, most local languages and dialects in Italy are at risk of disappearing within a few generations. The NLP community has recently begun to engage with endangered languages, including those of Italy. Yet, most efforts assume that these varieties are under-resourced language monoliths with an established written form and homogeneous functions and needs, and thus highly interchangeable with each other and with high-resource, standardized languages. In this paper, we introduce the linguistic context of Italy and challenge the default machine-centric assumptions of NLP for Italy’s language varieties. We advocate for a shift in the paradigm from machine-centric to speaker-centric NLP, and provide recommendations and opportunities for work that prioritizes languages and their speakers over technological advances. To facilitate the process, we finally propose building a local community towards responsible, participatory efforts aimed at supporting vitality of languages and dialects of Italy.

show abstract

Rule-Based Machine Translation for the Italian–Sardinian Language Pair

Cited by 3 publications

References 3 publications

Advanced techniques for domain adaptation in Statistical Machine Translation

Advanced techniques for domain adaptation in Statistical Machine Translation

Recent advances in Apertium, a free/open-source rule-based machine translation platform for low-resource languages

Language Varieties of Italy: Technology Challenges and Opportunities

Contact Info

Product

Resources

About