Proiektua

Helburuak

Partehartzaileak

Argitalpenak

Intranet

Demoak

Baliabideak eta tresnak

Zientzia-egoera 2008

Erreferentziak 2009

Helburuak


The aim of the project OpenMT-2 is to foster research in Machine Translation (MT) technology in order to generate robust, high-quality combined MT systems and improved evaluation metrics and methodologies. OpenMT-2 builds on the previous research carried out in the framework of the 2006-2008 OpenMT project (TIN2006-15307-C03-01). Current results in OpenMT are very satisfactory, and we foresee that further research on the basic working lines and also on some new research paths can provide much better results. The research in OpenMT-2 would be carried out in 5 main areas:

  • Collection, annotation and exploitation of multilingual corpora

  • Further development of the current single-paradigm translation systems

  • Pre-edition, post-edition and system improving based on collaboration with a web2.0 community.

  • Combining and hybridizing MT paradigms.

  • Advanced evaluation for MT

We will test the functionality of the new developed MT technology and systems with four different languages: English, Spanish, Catalan and Basque. Also, systems will be applied in different contexts (i.e., different corpora domains and genres).

The main innovative points of the proposal are:

  • The design of hybrid systems combining traditional linguistic rules, example-based methods and statistical methods

  • The use of advanced morphological, syntactic and semantic processing in MT

  • Research taking advantage of a web community of posteditors (2.0 oriented)

  • The use of more realistic metrics in MT evaluation, improving its reliability

  • The creation of a web-based suite of MT systems and tools for evaluation and error analysis

The consortium is composed by two universities: University of the Basque Country (UPV/EHU), Technical University of Catalonia (UPC), and a non-profit research centre: Elhuyar. Several companies and foundations with activities in closely related areas will serve as supervision EPOs for the project: Eleka, Fundaciķ i2CAT, Imaxin, Semantix, Translendium SL and eu.wikipedia.

Pil-Pilean



IXA taldea - EHU-UPV

Itzulpengintza automatiko neuronala. Jardunaldi irekia Kyunghyun Cho adituarekin (2017-05-29) 2017-Mai-16

IKERGAZTE sari bat Begoņa Altunari 2017-Mai-16

Mintegia: itzulpen automatikoa eta postedizio kolaboratiboa consumer.eus proiektuan (I. Cortes, 2017-05-09, 15:00) 2017-Mai-08

HITZ BESTE: Ez adiorik, Xuxen-zale amorratu hori 2017-Api-17

IXA-ko berri gehiago ikusi   



TALP Talk: Generative adversarial networks (GAN) applied to Speech Enhancement

Neural Machine Translation

Deep Dive in Deep Learning with TensorFlow

Mapping Unseen Words to Task-Trained Embedding Spaces

UPC-ko berri gehiago ikusi