Search
Now showing items 1-9 of 9
Multilingual word embeddings and their utility in cross-lingual learning
(2018-10-15)
Word embeddings - dense vector representations of a word’s distributional semantics - are an indespensable component of contemporary natural language processing (NLP). Bilingual embeddings, in particular, have attracted ...
Automating the anonymisation of textual corpora
(2018-11-04)
[EU] Gaur egun, testu berriak etengabe sortzen doaz sare sozialetako mezu, osasun-txosten,
dokumentu o zial eta halakoen ondorioz. Hala ere, testuok informazio pertsonala baldin
badute, ezin dira ikerkuntzarako edota ...
Noisy speech recognition using Kaldi and neural architectures
(2018-02)
[EN]Noisy Speech Recognition using Kaldi and Neural Architectures ABSTRACT The goal of an Automatic Speech Recognition (ASR) system is to transform a set of acoustic features into a sequence of words. It mainly consists ...
to post-edit or to translate ... That is the question: a case study of a recommender system for Quality Estimation of Machine Translation based on linguistic features
(2018)
[EN]The implementation of a machine translation system into production is not enough to warrant its efficient use. There exists the need to know when it is profitable to use machine translation as opposed to translating ...
Neural natural language generation with unstructured contextual information
(2018-11-04)
[EU] Lan honetan, hizkuntza naturalaren sorrera automatikoan informazio ez-egituratuaren esplotazioak izan dezakeen eragina aztertzen da. Bere helburu nagusia, sistema batek aurrez ikusi gabeko informazioa erabiliz testu ...
Unsupervised methods to predict example difficulty in word sense annotation
(2018-06)
[EU]Hitzen Adiera Desanbiguazioa (HAD) Hizkuntzaren Prozesamenduko (HP) erronkarik handienetakoa da. Frogatu denez, HAD sistema ahalik eta arrakastatsuenak entrenatzeko, oso garrantzitsua da entrenatze-datuetatik adibide ...
Elaboration of a RST Chinese Treebank
(2018-03-20)
[EN] As a subfield of Artificial Intelligence (AI), Natural Language Processing (NLP) aims to automatically process human languages. Fruitful achievements of variant studies from different research fields for NLP exist. ...
Basque-to-Spanish and Spanish-to-Basque machine translation for the health domain
(2018)
[EU]Master Amaierako Lan honek medikuntza domeinuko euskara eta gaztelera arteko itzulpen automatiko sistema bat garatzeko helburuarekin emandako lehenengo urratsak aurkezten ditu. Corpus elebidun nahikoaren faltan, hainbat ...
Analysis, overview and creation of an Arabic LVCSR
(2018-10-10)
As the standardized version of the Arabic Language, Modern Standard Arabic (MSA) is the most prevalent form of this language. MSA is also the third most spoken language in the world with over 300 million speakers. Moreover, ...