Zobrazeno 1 - 10
of 444
pro vyhledávání: '"Bassignana A"'
Autor:
Bassignana, Elisa, Gascou, Viggo Unmack, Laustsen, Frida Nøhr, Kristensen, Gustav, Petersen, Marie Haahr, van der Goot, Rob, Plank, Barbara
Current language models require a lot of training data to obtain high performance. For Relation Classification (RC), many datasets are domain-specific, so combining datasets to obtain better performance is non-trivial. We explore a multi-domain train
Externí odkaz:
http://arxiv.org/abs/2404.13760
Autor:
Barrett, Maria, Müller-Eberstein, Max, Bassignana, Elisa, Pauli, Amalie Brogaard, Zhang, Mike, van der Goot, Rob
Textual domain is a crucial property within the Natural Language Processing (NLP) community due to its effects on downstream model performance. The concept itself is, however, loosely defined and, in practice, refers to any non-typological property,
Externí odkaz:
http://arxiv.org/abs/2404.01785
Relation Extraction (RE) remains a challenging task, especially when considering realistic out-of-domain evaluations. One of the main reasons for this is the limited training size of current RE datasets: obtaining high-quality (manually annotated) da
Externí odkaz:
http://arxiv.org/abs/2305.11016
Most research in Relation Extraction (RE) involves the English language, mainly due to the lack of multi-lingual resources. We propose Multi-CrossRE, the broadest multi-lingual dataset for RE, including 26 languages in addition to English, and coveri
Externí odkaz:
http://arxiv.org/abs/2305.10985
With the increase in availability of large pre-trained language models (LMs) in Natural Language Processing (NLP), it becomes critical to assess their fit for a specific target task a priori - as fine-tuning the entire space of available LMs is compu
Externí odkaz:
http://arxiv.org/abs/2210.11255
Autor:
Bassignana, Elisa, Plank, Barbara
Relation Extraction (RE) has attracted increasing attention, but current RE evaluation is limited to in-domain evaluation setups. Little is known on how well a RE system fares in challenging, but realistic out-of-distribution evaluation setups. To ad
Externí odkaz:
http://arxiv.org/abs/2210.09345
Autor:
Bassignana, Elisa, Plank, Barbara
Over the last five years, research on Relation Extraction (RE) witnessed extensive progress with many new dataset releases. At the same time, setup clarity has decreased, contributing to increased difficulty of reliable empirical evaluation (Taill\'e
Externí odkaz:
http://arxiv.org/abs/2204.13516
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:
Bassignana, Giulia, Lacidogna, Giordano, Bartolomeo, Paolo, Colliot, Olivier, Fallani, Fabrizio De Vico
Understanding how few distributed areas can steer large-scale brain activity is a fundamental question that has practical implications, which range from inducing specific patterns of behavior to counteracting disease. Recent endeavors based on networ
Externí odkaz:
http://arxiv.org/abs/2112.07760
As a contribution to personality detection in languages other than English, we rely on distant supervision to create Personal-ITY, a novel corpus of YouTube comments in Italian, where authors are labelled with personality traits. The traits are deriv
Externí odkaz:
http://arxiv.org/abs/2011.07009