Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Daxenberger Johannes"'
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
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
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
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
Autor:
Trautmann, Dietrich, Daxenberger, Johannes, Stab, Christian, Schütze, Hinrich, Gurevych, Iryna
Prior work has commonly defined argument retrieval from heterogeneous document collections as a sentence-level classification task. Consequently, argument retrieval suffers both from low recall and from sentence segmentation errors making it difficul
Externí odkaz:
http://arxiv.org/abs/1904.09688
Argumentation mining (AM) requires the identification of complex discourse structures and has lately been applied with success monolingually. In this work, we show that the existing resources are, however, not adequate for assessing cross-lingual AM,
Externí odkaz:
http://arxiv.org/abs/1807.08998
We investigate whether and where multi-task learning (MTL) can improve performance on NLP problems related to argumentation mining (AM), in particular argument component identification. Our results show that MTL performs particularly well (and better
Externí odkaz:
http://arxiv.org/abs/1804.04083