Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Stefan Daniel Dumitrescu"'
Publikováno v:
Computer Science Journal of Moldova, Vol 21, Iss 3(63), Pp 332-359 (2013)
The benefits of using comparable corpora for improving translation quality for statistical machine translators have been already shown by various researchers. The usual approach is starting with a baseline system, trained on out-of-domain parallel co
Externí odkaz:
https://doaj.org/article/f4791a4d1fcc44fabcfb88de230697ec
Publikováno v:
Informatică economică, Vol 13, Iss 3, Pp 49-58 (2009)
This paper is an explanatory document about how several animations effects can be obtained using different numerical methods, as well as investigating the possibility of implementing them on very simple yet powerful massive parallel machines. The met
Externí odkaz:
https://doaj.org/article/e492c808c30546b2984deb0324041d16
Publikováno v:
CoNLL Shared Task (2)
We introduce NLP-Cube: an end-to-end Natural Language Processing framework, evaluated in CoNLL’s “Multilingual Parsing from Raw Text to Universal Dependencies 2018” Shared Task. It performs sentence splitting, tokenization, compound word expans
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9f2155d22d0a9a2baebe1caff53a8f7a
https://doi.org/10.18653/v1/k18-2017
https://doi.org/10.18653/v1/k18-2017
Publikováno v:
Human Language Technology. Challenges for Computer Science and Linguistics ISBN: 9783319937816
LTC
LTC
This work focuses on morphological analysis of raw text and provides a recipe for tokenization, sentence splitting and part-of-speech tagging for all languages included in the Universal Dependencies Corpus. Scalability is an important issue when deal
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6469c08e585577ad8ef3114187504877
https://doi.org/10.1007/978-3-319-93782-3_11
https://doi.org/10.1007/978-3-319-93782-3_11
Publikováno v:
RANLP
Decision trees have been previously employed in many machine-learning tasks such as part-of-speech tagging, lemmatization, morphological-attribute resolution, letter-to-sound conversion and statistical-parametric speech synthesis. In this paper we in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::351e909668d28bb3b2ccbbfc4bafe323
https://doi.org/10.26615/978-954-452-049-6_016
https://doi.org/10.26615/978-954-452-049-6_016
Publikováno v:
SpeD
This paper describes a data-driven approach to handling natural language interaction between humans and devices. This approach enables example-based definition and tuning of interaction scenarios. Actions and parameters can be easily configured, requ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1cb4fcc360defd8e9c4e8692181cd759
https://doi.org/10.1109/sped.2017.7990441
https://doi.org/10.1109/sped.2017.7990441
Autor:
Stefan Daniel Dumitrescu
Publikováno v:
SpeD
This paper presents the architecture and technologies used to develop a voice controlled system for home automation named Cassandra. We start with the goals of the project and a system description, then focusing on the main components and the way the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::07977d764f69032184a67a31992c28e1
https://doi.org/10.1109/sped.2017.7990440
https://doi.org/10.1109/sped.2017.7990440
Publikováno v:
EACL (Software Demonstrations)
Voice enabled human computer interfaces (HCI) that integrate automatic speech recognition, text-to-speech synthesis and natural language understanding have become a commodity, introduced by the immersion of smart phones and other gad- gets in our dai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a1b2c9d71281e861e669fc41e97872fb
https://doi.org/10.18653/v1/e17-3009
https://doi.org/10.18653/v1/e17-3009
Publikováno v:
CoNLL Shared Task (2)
This paper presents RACAI’s approach, experiments and results at CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. We handle raw text and we cover tokeniza tion, sentence splitting, word segmentation, tagging, le
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::87a399a56629266354775a65897891f4
https://doi.org/10.18653/v1/k17-3018
https://doi.org/10.18653/v1/k17-3018
Publikováno v:
Engineering Applications of Neural Networks ISBN: 9783319651712
EANN
EANN
We introduce a convolutional network architecture aimed at performing token-level processing in natural language applications. We tune this architecture for a specific task - multiword expression detection - and we compare our results to state-of-the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e26258aae632078d887c8052a26241e1
https://doi.org/10.1007/978-3-319-65172-9_13
https://doi.org/10.1007/978-3-319-65172-9_13