Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
End-to-End Argumentation Knowledge Graph Construction
Authors: Khalid Al-Khatib, Yufang Hou, Henning Wachsmuth, Charles Jochim, Francesca Bonin, Benno Stein7367-7374
AAAI 2020 | Venue PDF | LLM Run Details | Input Tokens: 16,621 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,923 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| 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. |