Zobrazeno 1 - 10
of 324
pro vyhledávání: '"A. Daxenberger"'
Most tasks in NLP require labeled data. Data labeling is often done on crowdsourcing platforms due to scalability reasons. However, publishing data on public platforms can only be done if no privacy-relevant information is included. Textual data ofte
Externí odkaz:
http://arxiv.org/abs/2303.03053
Publikováno v:
Revista Brasileira de Educação do Campo, Vol 9, Pp 1-25 (2024)
The general objective of the research is to map and identify which are the Universities and Federal Institutes of the northeast region that offer the Licentiate Degree in Rural Education course, and if the subject of Brazilian Sign Language (Libras)
Externí odkaz:
https://doaj.org/article/a26a16e47f7d4860a0ff6807ee7725b2
The task of Argument Mining, that is extracting and classifying argument components for a specific topic from large document sources, is an inherently difficult task for machine learning models and humans alike, as large Argument Mining datasets are
Externí odkaz:
http://arxiv.org/abs/2205.11472
Publikováno v:
Revista Educação e Emancipação, Vol 16, Iss 3, Pp 232-258 (2023)
Após vinte anos de promulgação da Lei 10.639/2002, ainda há muito o que se fazer quando pensamos o debate sobre o enfrentamento à discriminação, ao preconceito e ao racismo em um país de raízes escravocratas como Brasil. Neste sentido, o pre
Externí odkaz:
https://doaj.org/article/c486751d15f847629441a59276323dcc
There are two approaches for pairwise sentence scoring: Cross-encoders, which perform full-attention over the input pair, and Bi-encoders, which map each input independently to a dense vector space. While cross-encoders often achieve higher performan
Externí odkaz:
http://arxiv.org/abs/2010.08240
Sentence encoders map sentences to real valued vectors for use in downstream applications. To peek into these representations - e.g., to increase interpretability of their results - probing tasks have been designed which query them for linguistic kno
Externí odkaz:
http://arxiv.org/abs/2006.09109
We rely on arguments in our daily lives to deliver our opinions and base them on evidence, making them more convincing in turn. However, finding and formulating arguments can be challenging. In this work, we train a language model for argument genera
Externí odkaz:
http://arxiv.org/abs/2005.00084
Stance Detection (StD) aims to detect an author's stance towards a certain topic or claim and has become a key component in applications like fake news detection, claim validation, and argument search. However, while stance is easily detected by huma
Externí odkaz:
http://arxiv.org/abs/2001.01565
Publikováno v:
Revista de Iniciação à Docência, Vol 8, Iss 1 (2023)
Este artigo apresenta as atividades desenvolvidas no Programa de Apoio às Licenciaturas (Prolicen), com intervenções educativas como foco à Educação para as Relações Étnico-Raciais, de modo que fossem trabalhados aspectos que contribuíssem
Externí odkaz:
https://doaj.org/article/13ca6cc2e54d4bc7897af0ce1d65459a
Autor:
Reimers, Nils, Schiller, Benjamin, Beck, Tilman, Daxenberger, Johannes, Stab, Christian, Gurevych, Iryna
We experiment with two recent contextualized word embedding methods (ELMo and BERT) in the context of open-domain argument search. For the first time, we show how to leverage the power of contextualized word embeddings to classify and cluster topic-d
Externí odkaz:
http://arxiv.org/abs/1906.09821