Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Marcel Bollmann"'
Autor:
Heather Lent, Kushal Tatariya, Raj Dabre, Yiyi Chen, Marcell Fekete, Esther Ploeger, Li Zhou, Ruth-Ann Armstrong, Abee Eijansantos, Catriona Malau, Hans Erik Heje, Ernests Lavrinovics, Diptesh Kanojia, Paul Belony, Marcel Bollmann, Loïc Grobol, Miryam de Lhoneux, Daniel Hershcovich, Michel DeGraff, Anders Søgaard, Johannes Bjerva
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 12 (2024)
Externí odkaz:
https://doaj.org/article/72de20c83afb4f3dbd3816f3fb026064
Autor:
Anders Søgaard, Marcel Bollmann, Rahul Aralikatte, Daniel Hershcovich, Héctor Ricardo Murrieta Bello
Publikováno v:
Aralikatte, R, Murrieta Bello, H R, Hershcovich, D, Bollmann, M & Søgaard, A 2021, How far can we get with one GPU in 100 hours? CoAStaL at MultiIndicMT Shared Task . in Proceedings of the 8th Workshop on Asian Translation (WAT2021) . Association for Computational Linguistics, pp. 205-211, 8th Workshop on Asian Translation (WAT2021), Online, 05/08/2021 . https://doi.org/10.18653/v1/2021.wat-1.24
WAT@ACL/IJCNLP
WAT@ACL/IJCNLP
This work shows that competitive translation results can be obtained in a constrained setting by incorporating the latest advances in memory and compute optimization. We train and evaluate large multilingual translation models using a single GPU for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c25167e2558c91f0e949c85feeba6330
https://curis.ku.dk/portal/da/publications/how-far-can-we-get-with-one-gpu-in-100-hours(c3d3230a-c4a0-4fac-a8ee-5677d0b6c2e0).html
https://curis.ku.dk/portal/da/publications/how-far-can-we-get-with-one-gpu-in-100-hours(c3d3230a-c4a0-4fac-a8ee-5677d0b6c2e0).html
Autor:
Marcel Bollmann, Anders Søgaard
Publikováno v:
Bollmann, M & Søgaard, A 2021, Error analysis and the role of morphology . in EACL 2021-16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference . Association for Computational Linguistics, pp. 1887-1900, 16th Conference of the European Chapter of the Associationfor Computational Linguistics, EACL 2021, Virtual, Online, 19/04/2021 . < https://aclanthology.org/2021.eacl-main.162/ >
EACL
EACL
We evaluate two common conjectures in error analysis of NLP models: (i) Morphology is predictive of errors; and (ii) the importance of morphology increases with the morphological complexity of a language. We show across four different tasks and up to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c16f13f2d7ae87d0b5a00cdb7f1a4c4e
https://curis.ku.dk/portal/da/publications/error-analysis-and-the-role-of-morphology(1b5da8b8-090c-4724-bd7d-07a73902120b).html
https://curis.ku.dk/portal/da/publications/error-analysis-and-the-role-of-morphology(1b5da8b8-090c-4724-bd7d-07a73902120b).html
Autor:
Marcel Bollmann, Desmond Elliott
Publikováno v:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Bollmann, M M & Elliott, D 2020, On Forgetting to Cite Older Papers : An Analysis of the ACL Anthology . in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics . Association for Computational Linguistics, pp. 7819-7827, 58th Annual Meeting of the Association for Computational Linguistics, Online, 05/07/2020 . https://doi.org/10.18653/v1/2020.acl-main.699
ACL
Bollmann, M M & Elliott, D 2020, On Forgetting to Cite Older Papers : An Analysis of the ACL Anthology . in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics . Association for Computational Linguistics, pp. 7819-7827, 58th Annual Meeting of the Association for Computational Linguistics, Online, 05/07/2020 . https://doi.org/10.18653/v1/2020.acl-main.699
ACL
The field of natural language processing is experiencing a period of unprecedented growth, and with it a surge of published papers. This represents an opportunity for us to take stock of how we cite the work of other researchers, and whether this gro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ef35821ed23917d3215e9b897d80192d
Publikováno v:
RANLP
Neural machine translation models have little inductive bias, which can be a disadvantage in low-resource scenarios. Neural models have to be trained on large amounts of data and have been shown to perform poorly when only limited data is available.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::51cadcbe8fa372c94602f255c971f0e3
https://doi.org/10.26615/978-954-452-056-4_013
https://doi.org/10.26615/978-954-452-056-4_013
Publikováno v:
ACL (1)
Flachs, S, Bollmann, M & Søgaard, A 2019, Historical Text Normalization with Delayed Rewards . in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics . Association for Computational Linguistics, pp. 1614-1619, 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, 01/07/2019 . https://doi.org/10.18653/v1/P19-1157
Flachs, S, Bollmann, M & Søgaard, A 2019, Historical Text Normalization with Delayed Rewards . in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics . Association for Computational Linguistics, pp. 1614-1619, 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, 01/07/2019 . https://doi.org/10.18653/v1/P19-1157
Training neural sequence-to-sequence models with simple token-level log-likelihood is now a standard approach to historical text normalization, albeit often outperformed by phrase-based models. Policy gradient training enables direct optimization for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ff4f68d1b0f70d05fb873b53dfbedba5
https://doi.org/10.18653/v1/p19-1157
https://doi.org/10.18653/v1/p19-1157
Autor:
Marcel Bollmann
Publikováno v:
NAACL-HLT (1)
Bollmann, M 2019, A Large-Scale Comparison of Historical Text Normalization Systems . in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) . Association for Computational Linguistics, pp. 3885-3898, 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies-NAACL-HLT 2019, Minneapolis, United States, 03/06/2019 . https://doi.org/10.18653/v1/N19-1389
Bollmann, M 2019, A Large-Scale Comparison of Historical Text Normalization Systems . in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) . Association for Computational Linguistics, pp. 3885-3898, 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies-NAACL-HLT 2019, Minneapolis, United States, 03/06/2019 . https://doi.org/10.18653/v1/N19-1389
There is no consensus on the state-of-the-art approach to historical text normalization. Many techniques have been proposed, including rule-based methods, distance metrics, character-based statistical machine translation, and neural encoder--decoder
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ee3599f8ddfbe0c79a7fe6646f8cc5a9
https://doi.org/10.18653/v1/n19-1389
https://doi.org/10.18653/v1/n19-1389
Publikováno v:
DeepLo@EMNLP-IJCNLP
Bollmann, M, Korchagina, N & Søgaard, A 2019, Few-Shot and Zero-Shot Learning for Historical Text Normalization . in Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019) . Association for Computational Linguistics, pp. 104-114, 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo), Hong Kong, China, 03/11/2019 . https://doi.org/10.18653/v1/D19-6112
Bollmann, M, Korchagina, N & Søgaard, A 2019, Few-Shot and Zero-Shot Learning for Historical Text Normalization . in Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019) . Association for Computational Linguistics, pp. 104-114, 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo), Hong Kong, China, 03/11/2019 . https://doi.org/10.18653/v1/D19-6112
Historical text normalization often relies on small training datasets. Recent work has shown that multi-task learning can lead to significant improvements by exploiting synergies with related datasets, but there has been no systematic study of differ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1b04329088cd4c216273ed086ae54f6c
https://doi.org/10.18653/v1/d19-6112
https://doi.org/10.18653/v1/d19-6112
Publikováno v:
Journal for Language Technology and Computational Linguistics. 31:1-15
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8289ffadea5d2070aa0342295535645b
https://doi.org/10.21248/jlcl.31.2016.208
https://doi.org/10.21248/jlcl.31.2016.208
Autor:
Marcel Bollmann
Publikováno v:
Ruhr-Universität Bochum
Marcel Bollmann
Marcel Bollmann
Historische Dokumente werden zunehmend in digitalisierter Form verfügbar gemacht. Häufig sind sie jedoch durch eine Fülle von Schreibvarianten gekennzeichnet, welche die Anwendung computerlinguistischer Methoden (bzw. NLP-Tools) schwierig gestalte
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fd3b8da22dd333818a2c7cefeed4f2b2
https://hss-opus.ub.ruhr-uni-bochum.de/opus4/files/6213/diss.pdf
https://hss-opus.ub.ruhr-uni-bochum.de/opus4/files/6213/diss.pdf