Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Stephanie Brandl"'
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 11, Pp 320-335 (2023)
AbstractComplementary to finding good general word embeddings, an important question for representation learning is to find dynamic word embeddings, for example, across time or domain. Current methods do not offer a way to use or predict information
Externí odkaz:
https://doaj.org/article/1c053c080fa943c5ac0cf5cfaf1d67e5
Autor:
Stephanie Brandl, Benjamin Blankertz
Publikováno v:
Frontiers in Neuroscience, Vol 14 (2020)
Externí odkaz:
https://doaj.org/article/9a7dd499ed99463fb80b6443f63feafb
Autor:
Stephanie Brandl, Nora Hollenstein
Publikováno v:
Brandl, S & Hollenstein, N 2022, Every word counts: A multilingual analysis of individual human alignment with model attention . in Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers) . Association for Computational Linguistics, pp. 72-77 . < https://aclanthology.org/2022.aacl-short.10 >
University of Copenhagen
University of Copenhagen
Human fixation patterns have been shown to correlate strongly with Transformer-based attention. Those correlation analyses are usually carried out without taking into account individual differences between participants and are mostly done on monoling
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3a6beaea472d0d98f6b666bec9d75578
http://arxiv.org/abs/2210.04963
http://arxiv.org/abs/2210.04963
Publikováno v:
Morger, F, Brandl, S, Beinborn, L & Hollenstein, N 2022, A Cross-lingual Comparison of Human and Model Relative Word Importance . i Proceedings of the 2022 CLASP Conference on (Dis)embodiment . Association for Computational Linguistics (ACL), s. 11-23, 2022 CLASP Conference on (Dis)embodiment, Gothenburg / Online, Sverige, 15/09/2022 . < https://aclanthology.org/2022.clasp-1.2 >
University of Copenhagen
University of Copenhagen
Relative word importance is a key metric for natural language processing. In this work, we compare human and model relative word importance to investigate if pretrained neural language models focus on the same words as humans cross-lingually. We perf
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::3815dcd44f1b3333cf00bd0b260d97db
https://curis.ku.dk/ws/files/335430688/A_Cross_lingual_Comparison_of_Human_and_Model_Relative_Word.pdf
https://curis.ku.dk/ws/files/335430688/A_Cross_lingual_Comparison_of_Human_and_Model_Relative_Word.pdf
Publikováno v:
Eberle, O, Brandl, S, Pilot, J & Søgaard, A 2022, Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze? in S Muresan, P Nakov & A Villavicencio (eds), ACL 2022-60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) . Association for Computational Linguistics (ACL), Proceedings of the Annual Meeting of the Association for Computational Linguistics, vol. 1, pp. 4295-4309, 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022, Dublin, Ireland, 22/05/2022 . https://doi.org/10.18653/v1/2022.acl-long.296
Learned self-attention functions in state-of-the-art NLP models often correlate with human attention. We investigate whether self-attention in large-scale pre-trained language models is as predictive of human eye fixation patterns during task-reading
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d79b062d84778e0fa5b4d732712caf00
http://arxiv.org/abs/2205.10226
http://arxiv.org/abs/2205.10226
Autor:
Daniel Hershcovich, Stella Frank, Heather Lent, Miryam de Lhoneux, Mostafa Abdou, Stephanie Brandl, Emanuele Bugliarello, Laura Cabello Piqueras, Ilias Chalkidis, Ruixiang Cui, Constanza Fierro, Katerina Margatina, Phillip Rust, Anders Søgaard
Publikováno v:
Hershcovich, D, Frank, S, Lent, H, de Lhoneux, M, Abdou, M, Brandl, S, Bugliarello, E, Piqueras, L C, Chalkidis, I, Cui, R, Fierro, C, Margatina, K, Rust, P & Søgaard, A 2022, Challenges and Strategies in Cross-Cultural NLP . in S Muresan, P Nakov & A Villavicencio (eds), ACL 2022-60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) . vol. 1, Association for Computational Linguistics (ACL), pp. 6997-7013, 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022, Dublin, Ireland, 22/05/2022 . https://doi.org/10.18653/v1/2022.acl-long.482
Various efforts in the Natural Language Processing (NLP) community have been made to accommodate linguistic diversity and serve speakers of many different languages. However, it is important to acknowledge that speakers and the content they produce a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b4657ac922e1a12d4385c99c3d3ffbba
http://arxiv.org/abs/2203.10020
http://arxiv.org/abs/2203.10020
Autor:
Peter Vuust, Stephanie Brandl, S. Radloff, Niels Trusbak Haumann, Manon Grube, Elvira Brattico, Leonardo Bonetti, Sven Dähne
We propose here (the informed use) of a customised, data-driven machine-learning pipeline to analyse magnetoencephalography (MEG) in a theoretical source space, with respect to the processing of a regular beat. This hypothesis- and data-driven analys
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::485dd24711c5055206696e374dad47af
https://doi.org/10.1101/2021.04.23.441088
https://doi.org/10.1101/2021.04.23.441088
Autor:
Stephanie Brandl, Waldemar Berg, Marcus Herntrei, Georg Christian Steckenbauer, Suzanne Lachmann-Falkner, Lahoucine Amzil, Heike Bähre, Monika Bandi Tanner, Christian Baumgartner, Linda Bitsch, Vanessa Borkmann, Birgit Bosio, Armin A. Brysch, Christian Eilzer, Bernd Eisenstein, Brahim Elfasskaoui, Valerie Isabel Elss, Ulrike Fergen, Verena Frank, Michael Fux, Sven Groß, Jon Hanf, Tim Harms, Christian Hausy, Felix Bernhard Herle, Andreas Kagermeier, Anna Klein, Pascal Mandelartz, Monica Nadegger, Natalie Olbrich, Ina Oven-Krockhaus, Markus Pillmayer, Maria Ragaller, Jens Rüdiger, Manuel Sand, Roland Schegg, Nicolai Scherle, Dirk Schmücker, Carolin Steinhauser, Nico Stengel, Johannes Treu, Samuel Wirth, Annegret Wittmann-Wurzer, Peter Wolff, Nicola Zech
Publikováno v:
Schriften zu Tourismus und Freizeit ISBN: 9783503195312
Ob die Sehnsucht nach Natur, der Wunsch nach Abstand oder eine Suche nach unverfälschten, authentischen Erlebnissen: Das wachsende Interesse vieler Reisenden am Landleben und ländlichen Regionen birgt unzählige Chancen und Spannungsfelder in der T
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2b96973d16963d375178801fdfb338d5
https://doi.org/10.37307/b.978-3-503-19531-2
https://doi.org/10.37307/b.978-3-503-19531-2
Autor:
David Lassner, Stephanie Brandl
We propose Word Embedding Networks, a novel method that is able to learn word embeddings of individual data slices while simultaneously aligning and ordering them without feeding temporal information a priori to the model. This gives us the opportuni
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::701c7fb2c16be976a20fdcb006fc28ec
https://depositonce.tu-berlin.de/handle/11303/11575
https://depositonce.tu-berlin.de/handle/11303/11575
Autor:
Julia Böck, Katja Maurus, Elena Gerhard-Hartmann, Stephanie Brändlein, Katrin S. Kurz, German Ott, Ioannis Anagnostopoulos, Andreas Rosenwald, Alberto Zamò
Publikováno v:
Frontiers in Oncology, Vol 13 (2023)
Diagnosing any of the more than 30 types of T-cell lymphomas is considered a challenging task for many pathologists and currently requires morphological expertise as well as the integration of clinical data, immunophenotype, flow cytometry and clonal
Externí odkaz:
https://doaj.org/article/e2abd8b5956b43c080db509510797b81