End-to-End Argumentation Knowledge Graph Construction

Authors: Khalid Al-Khatib, Yufang Hou, Henning Wachsmuth, Charles Jochim, Francesca Bonin, Benno Stein7367-7374

AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The results of experiments show the potential of the framework for building a web-based argumentation graph that is of high quality and large scale. Our approach achieves a macro F1-score of 0.79 in detecting relations and 0.77 in classifying their types.
Researcher Affiliation Collaboration Khalid Al-Khatib,1 Yufang Hou,2 Henning Wachsmuth,3 Charles Jochim,2 Francesca Bonin,2 Benno Stein1 1Bauhaus-Universitat Weimar, Germany 2IBM Research, Ireland 3Paderborn University, Germany
Pseudocode No The paper describes methods and processes but does not include explicit pseudocode or algorithm blocks.
Open Source Code Yes The developed resources are freely available on webis.de.
Open Datasets Yes We used the complete dataset of Hou and Jochim (2017). The developed resources are freely available on webis.de. ... Annotated English Gigaword (Napoles, Gormley, and Durme 2012)
Dataset Splits No The paper states: 'we split the corpus into training (80%) and test (20%) sets'. It does not explicitly mention a separate validation split from the main corpus.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory) used for running experiments are provided in the paper.
Software Dependencies No The paper mentions software like NLTK, Textblob, and Scikit-learn, but does not provide specific version numbers for these libraries or other software dependencies.
Experiment Setup No The paper mentions 'The C value is optimized using grid search on the training dataset' but does not provide the specific hyperparameter values (e.g., learning rate, batch size, number of epochs, or the optimized C value) used in the final experimental setup.