Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Falenska, A."'
The rise of populism concerns many political scientists and practitioners, yet the detection of its underlying language remains fragmentary. This paper aims to provide a reliable, valid, and scalable approach to measure populist stances. For that pur
Externí odkaz:
http://arxiv.org/abs/2309.14355
Instructional texts for specific target groups should ideally take into account the prior knowledge and needs of the readers in order to guide them efficiently to their desired goals. However, targeting specific groups also carries the risk of reflec
Externí odkaz:
http://arxiv.org/abs/2309.12117
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Falenska, Agnieszka, Kuhn, Jonas
Classical non-neural dependency parsers put considerable effort on the design of feature functions. Especially, they benefit from information coming from structural features, such as features drawn from neighboring tokens in the dependency tree. In c
Externí odkaz:
http://arxiv.org/abs/1905.12676
Publikováno v:
Proceedings of the PolEval 2018 Workshop, 2018, 25-39
This paper presents the IMS contribution to the PolEval 2018 Shared Task. We submitted systems for both of the Subtasks of Task 1. In Subtask (A), which was about dependency parsing, we used our ensemble system from the CoNLL 2017 UD Shared Task. The
Externí odkaz:
http://arxiv.org/abs/1811.03036
We present a general-purpose tagger based on convolutional neural networks (CNN), used for both composing word vectors and encoding context information. The CNN tagger is robust across different tagging tasks: without task-specific tuning of hyper-pa
Externí odkaz:
http://arxiv.org/abs/1706.01723
Autor:
Agnieszka Falenska, Özlem Çetinoğlu
Publikováno v:
Proceedings of the 3rd Workshop on Gender Bias in Natural Language Processing.
Potential gender biases existing in Wikipedia’s content can contribute to biased behaviors in a variety of downstream NLP systems. Yet, efforts in understanding what inequalities in portraying women and men occur in Wikipedia focused so far only on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a0ad1aa6463177d2665243bbb709ae0e
https://doi.org/10.18653/v1/2021.gebnlp-1.9
https://doi.org/10.18653/v1/2021.gebnlp-1.9
Publikováno v:
IWPT 2020
Graph-based and transition-based dependency parsers used to have different strengths and weaknesses. Therefore, combining the outputs of parsers from both paradigms used to be the standard approach to improve or analyze their performance. However, wi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1e9f952d8febe1eed0ccb62592df484f
https://doi.org/10.18653/v1/2020.iwpt-1.4
https://doi.org/10.18653/v1/2020.iwpt-1.4
Autor:
Agnieszka Falenska, Jonas Kuhn
Publikováno v:
ACL (1)
Classical non-neural dependency parsers put considerable effort on the design of feature functions. Especially, they benefit from information coming from structural features, such as features drawn from neighboring tokens in the dependency tree. In c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f2bf1f1080819c2553715207d9fd6f25
http://arxiv.org/abs/1905.12676
http://arxiv.org/abs/1905.12676
Publikováno v:
MSR@EMNLP-IJCNLP
We introduce the IMS contribution to the Surface Realization Shared Task 2019. Our submission achieves the state-of-the-art performance without using any external resources. The system takes a pipeline approach consisting of five steps: linearization
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0c69f43f55a03ad1f953bdd50cbe44ef
https://doi.org/10.18653/v1/d19-6306
https://doi.org/10.18653/v1/d19-6306