Exploració per tema "Traducció automàtica"
Ara es mostren els items 41-60 de 153
-
English-catalan neural machine translation in the biomedical domain through the cascade approach
(2018)
Comunicació de congrés
Accés restringit per política de l'editorialThis paper describes the methodology followed to build a neural machine translation system in the biomedical domain for the English-Catalan language pair. This task can be considered a low-resourced task from the point of ... -
English-to-Hindi system description for WMT 2014: deep source-context features for Moses
(Association for Computational Linguistics, 2014)
Comunicació de congrés
Accés obertThis paper describes the IPN-UPV participation on the English-to-Hindi translation task from WMT 2014 International Evaluation Campaign. The system presented is based on Moses and enhanced with deep learning by meansof ... -
Enhancing scarce-resource language translation through pivot combinations
(2011)
Text en actes de congrés
Accés obertChinese and Spanish are the most spoken languages in the world. However, there is not much research done in machine translation for this language pair. We experiment with the parallel Chinese-Spanish corpus (United Nations) ... -
Enriching the transformer with linguistic factors for low-resource machine translation
(Incoma, Ltd., 2021)
Text en actes de congrés
Accés obertIntroducing factors, that is to say, word features such as linguistic information referring to the source tokens, is known to improve the results of neural machine translation systems in certain settings, typically in ... -
Evaluating gender bias in speech translation
(European Language Resources Association, 2022)
Comunicació de congrés
Accés obertThe scientific community is increasingly aware of the necessity to embrace pluralism and consistently represent major and minor social groups. Currently, there are no standard evaluation techniques for different types of ... -
Experimental research on encoder-decoder architectures with attention for chatbots
(2018-03-18)
Article
Accés restringit per política de l'editorialChatbots aim at automatically offering a conversation be- tween a human and a computer. While there is a long track of re- search in rule-based and retrieval-based approaches, the generation-based approaches are promisingly ... -
Experiments on document level machine translation
(2014-03-03)
Report de recerca
Accés obertMost of the current SMT systems work at sentence level. They translate a text assuming that sentences are independent, but, when one looks at a well formed document, it is clear that there exist many inter sentence relations. ... -
Explaining how transformers use context to build predictions
(Association for Computational Linguistics, 2023)
Comunicació de congrés
Accés obertLanguage Generation Models produce words based on the previous context. Although existing methods offer input attributions as explanations for a model’s prediction, it is still unclear how prior words affect the model’s ... -
Explaining how transformers use context to build predictions
(2023-05-21)
Report de recerca
Accés obertLanguage Generation Models produce words based on the previous context. Although existing methods offer input attributions as explanations for a model's prediction, it is still unclear how prior words affect the model's ... -
Exploratori visual analysis of machine translaton systems
(Universitat Politècnica de Catalunya, 2019-07-04)
Projecte Final de Màster Oficial
Accés obertThis project aims to provide visualisation tools for helping researchers to understand their model. We are now able to visualise multilingual intermediate representations. We can also visualise multilingual representations ... -
Exploring lifelong learning in neural machine translation
(Universitat Politècnica de Catalunya, 2021-07-06)
Projecte Final de Màster Oficial
Accés obertLifelong learning is a technique defined as the ability to learn newor maintain older knowledge over time. This factor is very important for humans, as it is one of the keys to the ability to learn by humans, which artificial ... -
Findings of the first shared task on lifelong learning machine translation
(Association for Computational Linguistics, 2020)
Comunicació de congrés
Accés obertA lifelong learning system can adapt to new data without forgetting previously acquired knowledge. In this paper, we introduce the first benchmark for lifelong learning machine translation. For this purpose, we provide ... -
Fine-tuning neural machine translation on gender-balanced datasets
(Association for Computational Linguistics, 2020)
Comunicació de congrés
Accés obertMisrepresentation of certain communities in datasets is causing big disruptions in artificial intelligence applications. In this paper, we propose using an automatically extracted gender-balanced dataset parallel corpus ... -
From bilingual to multilingual neural machine translation by incremental training
(Association for Computational Linguistics, 2019)
Comunicació de congrés
Accés obertMultilingual Neural Machine Translation approaches are based on the use of task specific models and the addition of one more language can only be done by retraining the whole system. In this work, we propose a new training ... -
From bilingual to multilingual neural-based machine translation by incremental training
(2020-08-02)
Article
Accés obertA common intermediate language representation in neural machine translation can be used to extend bilingual systems by incremental training. We propose a new architecture based on introducing an interlingual loss as an ... -
GeBioToolkit: automatic extraction of gender-balanced multilingual corpus of Wikipedia biographies
(European Language Resources Association (ELRA), 2020)
Comunicació de congrés
Accés obertWe introduce GeBioToolkit, a tool for extracting multilingual parallel corpora at sentence level, with document and gender information from Wikipedia biographies. Despite the gender inequalities present in Wikipedia, the ... -
Gender bias in multilingual neural machine translation: The architecture matters
(2020-12-24)
Report de recerca
Accés obertMultilingual Neural Machine Translation architectures mainly differ in the amount of sharing modules and parameters among languages. In this paper, and from an algorithmic perspective, we explore if the chosen architecture, ... -
Gender bias in neural machine translation: The case of indian languages
(Universitat Politècnica de Catalunya, 2020-06)
Treball Final de Grau
Accés obertLa traducció automàtica implica la traducció de text d'un idioma a un altre amb ajuda d'un sistema automàtic. En concret, la traducció automàtica neuronal implica l'ús d'una arquitectura basada en xarxes neuronals. Aquest ... -
High frequent in-domain word segmentation and forward translation for the WMT21 Biomedical task
(Association for Computational Linguistics, 2021)
Text en actes de congrés
Accés obertThis paper reports the optimization of using the out-of-domain data in the Biomedical translation task. We firstly optimized our parallel training dataset using the BabelNet in-domain terminology words. Afterward, to ... -
How much hybridisation does machine translation need?
(2015-10-01)
Article
Accés obertRule-based and corpus-based machine translation (MT)have coexisted for more than 20 years. Recently, bound-aries between the two paradigms have narrowed andhybrid approaches are gaining interest from bothacademia and ...