Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Varab, Daniel"'
Autor:
Varab, Daniel, Hardmeier, Christian
Recent work has suggested that end-to-end system designs for cross-lingual summarization are competitive solutions that perform on par or even better than traditional pipelined designs. A closer look at the evidence reveals that this intuition is bas
Externí odkaz:
http://arxiv.org/abs/2409.00414
Autor:
Ulmer, Dennis, Bassignana, Elisa, Müller-Eberstein, Max, Varab, Daniel, Zhang, Mike, van der Goot, Rob, Hardmeier, Christian, Plank, Barbara
The field of Deep Learning (DL) has undergone explosive growth during the last decade, with a substantial impact on Natural Language Processing (NLP) as well. Yet, compared to more established disciplines, a lack of common experimental standards rema
Externí odkaz:
http://arxiv.org/abs/2204.06251
Autor:
Strømberg-Derczynski, Leon, Ciosici, Manuel R., Baglini, Rebekah, Christiansen, Morten H., Dalsgaard, Jacob Aarup, Fusaroli, Riccardo, Henrichsen, Peter Juel, Hvingelby, Rasmus, Kirkedal, Andreas, Kjeldsen, Alex Speed, Ladefoged, Claus, Nielsen, Finn Årup, Petersen, Malte Lau, Rystrøm, Jonathan Hvithamar, Varab, Daniel
Danish language technology has been hindered by a lack of broad-coverage corpora at the scale modern NLP prefers. This paper describes the Danish Gigaword Corpus, the result of a focused effort to provide a diverse and freely-available one billion wo
Externí odkaz:
http://arxiv.org/abs/2005.03521
Autor:
Varab, Daniel, Schluter, Natalie
This paper describes the design and use of the graph-based parsing framework and toolkit UniParse, released as an open-source python software package. UniParse as a framework novelly streamlines research prototyping, development and evaluation of gra
Externí odkaz:
http://arxiv.org/abs/1807.04053
Autor:
Ulmer, Dennis Thomas, Bassignana, Elisa, Müller-Eberstein, Max, Varab, Daniel, Zhang, Mike, Hardmeier, Christian, Plank, Barbara
Publikováno v:
Ulmer, D T, Bassignana, E, Müller-Eberstein, M, Varab, D, Zhang, M, Hardmeier, C & Plank, B 2022, ' Experimental Standards for Deep Learning Research: A Natural Language Processing Perspective ' .
The field of Deep Learning (DL) has undergone explosive growth during the last decade, with a substantial impact on Natural Language Processing (NLP) as well. Yet, as with other fields employing DL techniques, there has been a lack of common experime
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2988::44eee2e89ec3f70eedfabdedd9ccc56e
https://pure.itu.dk/portal/da/publications/fc23a8ce-731e-4697-aad6-c6f8388c5a44
https://pure.itu.dk/portal/da/publications/fc23a8ce-731e-4697-aad6-c6f8388c5a44
Autor:
Strømberg-Derczynski, Leon, Ciosici, Manuel Rafael, Christiansen, Morten H., Baglini, Rebekah Brita, Dalsgaard, Jacob Aarup, Fusaroli, Riccardo, Henrichsen, Peter Juel, Hvingelby, Rasmus, Kirkedal, Andreas, Kjeldsen, Alex Speed, Ladefoged, Claus, Nielsen, Finn Arup, Madsen, Jens, Petersen, Malte Lau, Rystrøm, Jonathan Hvithamar, Varab, Daniel
Publikováno v:
Strømberg-Derczynski, L, Ciosici, M R, Christiansen, M H, Baglini, R B, Dalsgaard, J A, Fusaroli, R, Henrichsen, P J, Hvingelby, R, Kirkedal, A, Kjeldsen, A S, Ladefoged, C, Nielsen, F A, Madsen, J, Petersen, M L, Rystrøm, J H & Varab, D 2021, The Danish Gigaword Corpus . in Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa) . Linköping University Electronic Press, pp. 413-421 . < https://www.aclweb.org/anthology/2021.nodalida-main.46 >
Danish language technology has been hindered by a lack of broad-coverage corpora at the scale modern NLP prefers. This paper describes the Danish Gigaword Corpus, the result of a focused effort to provide a diverse and freely-available one billion wo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2751::40d0d6ef0a8ba840b1ac2f6cc3e8a1eb
https://curis.ku.dk/ws/files/305020079/2021.nodalida_main.46v2.pdf
https://curis.ku.dk/ws/files/305020079/2021.nodalida_main.46v2.pdf
Autor:
Varab, Daniel, Schluter, Natalie
Publikováno v:
Varab, D & Schluter, N 2020, DaNewsroom: A Large-scale Danish Summarisation Dataset . in Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020) . European Language Resources Association, pp. 6731–6739 . < https://www.aclweb.org/anthology/2020.lrec-1.831/ >
Dataset development for automatic summarisation systems is notoriously English-oriented. In this paper we present the first large-scale non-English language dataset specifically curated for automatic summarisation. The document-summary pairs are news
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2988::437dbefbf0501edb87b0d3c373a6b5be
https://pure.itu.dk/portal/da/publications/448828b4-0d75-48e9-9841-9ad54c8b2727
https://pure.itu.dk/portal/da/publications/448828b4-0d75-48e9-9841-9ad54c8b2727