Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Raivis Skadiņš"'
Publikováno v:
Applied Sciences, Vol 10, Iss 21, p 7426 (2020)
Accurate intent detection-based chatbots are usually trained on larger datasets that are not available for some languages. Seeking the most accurate models, three English benchmark datasets that were human-translated into four morphologically complex
Externí odkaz:
https://doaj.org/article/453b50d6ceaa4824bdef16489f73b1c1
Autor:
Daiga Deksne, Raivis Skadiņš
Publikováno v:
Proceedings of the Future Technologies Conference (FTC) 2022, Volume 3 ISBN: 9783031183430
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::db12527bcfd1354ff7995c7ade47131f
https://doi.org/10.1007/978-3-031-18344-7_39
https://doi.org/10.1007/978-3-031-18344-7_39
Autor:
Inguna Skadiņa, Baiba Saulīte, Ilze Auziņa, Normunds Grūzītis, Andrejs Vasiļjevs, Raivis Skadiņš, Mārcis Pinnis
Publikováno v:
Baltic Journal of Modern Computing. 10
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a8ae80f6f3530198fc5cf520f4957ace
https://doi.org/10.22364/bjmc.2022.10.3.21
https://doi.org/10.22364/bjmc.2022.10.3.21
Autor:
Daiga Deksne, Raivis Skadiņš
Publikováno v:
Proceedings of the Future Technologies Conference (FTC) 2021, Volume 1 ISBN: 9783030899059
This paper reports on creating a neural network model for prediction of the next action in a dialogue considering conversation history, i.e. entities, context variables and emotion indicators marking emotionally loaded user utterances. Several experi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8a9de1d23ab681c4af06cc8b902f3b21
https://doi.org/10.1007/978-3-030-89906-6_19
https://doi.org/10.1007/978-3-030-89906-6_19
Publikováno v:
Electronics
Electronics, MDPI, 2021, 10, ⟨10.3390/electronics10121412⟩
Electronics, Vol 10, Iss 1412, p 1412 (2021)
Volume 10
Issue 12
Electronics, MDPI, 2021, 10, ⟨10.3390/electronics10121412⟩
Electronics, Vol 10, Iss 1412, p 1412 (2021)
Volume 10
Issue 12
Due to recent DNN advancements, many NLP problems can be effectively solved using transformer-based models and supervised data. Unfortunately, such data is not available in some languages. This research is based on assumptions that (1) training data
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c4d88bf7eb1dd93a17eaea08360a01ea
https://hal.inria.fr/hal-03351013/file/kapociute-dzikiene_Electronics2021.pdf
https://hal.inria.fr/hal-03351013/file/kapociute-dzikiene_Electronics2021.pdf
Autor:
Andrejs Vasiļjevs, Andreas Eisele, Yu Chen, Raivis Skadiņš, Xiaojun Zhang, Bogdan Babych, Sabine Hunsicker, Inguna Skadiņa, Mārcis Pinnis, Mateja Verlic, Gregor Thurmair
Publikováno v:
Using Comparable Corpora for Under-Resourced Areas of Machine Translation ISBN: 9783319990033
Using Comparable Corpora for Under-Resourced Areas of Machine Translation
Using Comparable Corpora for Under-Resourced Areas of Machine Translation
This chapter describes how semi-parallel and parallel data extracted from comparable corpora can be used in enhancing machine translation (MT) systems: what are the methods used for this task in statistical and rule-based machine translation systems;
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2f7467b212ba06571f4619a1427dedde
https://doi.org/10.1007/978-3-319-99004-0_6
https://doi.org/10.1007/978-3-319-99004-0_6
Publikováno v:
Applied Sciences, Vol 10, Iss 7426, p 7426 (2020)
Applied Sciences
Volume 10
Issue 21
Applied Sciences
Volume 10
Issue 21
Accurate intent detection-based chatbots are usually trained on larger datasets that are not available for some languages. Seeking the most accurate models, three English benchmark datasets that were human-translated into four morphologically complex
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::93925fe538fa57d17c31ecaf81b98615
https://doi.org/10.3390/app10217426
https://doi.org/10.3390/app10217426
Publikováno v:
Natural Language Processing and Information Systems ISBN: 9783319919461
NLDB
NLDB
In this paper, we present our work on integrating neural machine translation systems in the document translation workflow of the cloud-based machine translation platform Tilde MT. We describe the functionality of the translation workflow and provide
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2f509cb3c38f1084744567fc8c59031d
https://doi.org/10.1007/978-3-319-91947-8_51
https://doi.org/10.1007/978-3-319-91947-8_51
Publikováno v:
Computational Linguistics and Intelligent Text Processing ISBN: 9783642549052
CICLing (1)
CICLing (1)
This paper reports on the implementation of grammar checkers and parsers for highly inflected and under-resourced languages. As classical context free grammar CFG formalism performs poorly on languages with a rich morphological feature system, we hav
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a8005d7327ff8cfa463ecaa8c413534e
https://doi.org/10.1007/978-3-642-54906-9_19
https://doi.org/10.1007/978-3-642-54906-9_19
Publikováno v:
Natural Language Processing and Information Systems ISBN: 9783319079820
NLDB
NLDB
Virtual agent is a powerful means for human-computer interaction. In this demo paper, we describe a new scenario for mobile virtual agent that, in addition to general social intelligence, can perform translation tasks. We present the design and devel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e8e9c88218727d6e8b6f32334d20609c
https://doi.org/10.1007/978-3-319-07983-7_38
https://doi.org/10.1007/978-3-319-07983-7_38