Which Side Are You On? A Multi-task Dataset for End-to-End Argument Summarisation and Evaluation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917753391153152 |
|---|---|
| author | Li, Hao Wu, Yuping Schlegel, Viktor Batista-Navarro, Riza Madusanka, Tharindu Zahid, Iqra Zeng, Jiayan Wang, Xiaochi He, Xinran Li, Yizhi Nenadic, Goran |
| author_facet | Li, Hao Wu, Yuping Schlegel, Viktor Batista-Navarro, Riza Madusanka, Tharindu Zahid, Iqra Zeng, Jiayan Wang, Xiaochi He, Xinran Li, Yizhi Nenadic, Goran |
| contents | With the recent advances of large language models (LLMs), it is no longer infeasible to build an automated debate system that helps people to synthesise persuasive arguments. Previous work attempted this task by integrating multiple components. In our work, we introduce an argument mining dataset that captures the end-to-end process of preparing an argumentative essay for a debate, which covers the tasks of claim and evidence identification (Task 1 ED), evidence convincingness ranking (Task 2 ECR), argumentative essay summarisation and human preference ranking (Task 3 ASR) and metric learning for automated evaluation of resulting essays, based on human feedback along argument quality dimensions (Task 4 SQE). Our dataset contains 14k examples of claims that are fully annotated with the various properties supporting the aforementioned tasks. We evaluate multiple generative baselines for each of these tasks, including representative LLMs. We find, that while they show promising results on individual tasks in our benchmark, their end-to-end performance on all four tasks in succession deteriorates significantly, both in automated measures as well as in human-centred evaluation. This challenge presented by our proposed dataset motivates future research on end-to-end argument mining and summarisation. The repository of this project is available at https://github.com/HaoBytes/ArgSum-Datatset |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_03151 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Which Side Are You On? A Multi-task Dataset for End-to-End Argument Summarisation and Evaluation Li, Hao Wu, Yuping Schlegel, Viktor Batista-Navarro, Riza Madusanka, Tharindu Zahid, Iqra Zeng, Jiayan Wang, Xiaochi He, Xinran Li, Yizhi Nenadic, Goran Computation and Language Machine Learning With the recent advances of large language models (LLMs), it is no longer infeasible to build an automated debate system that helps people to synthesise persuasive arguments. Previous work attempted this task by integrating multiple components. In our work, we introduce an argument mining dataset that captures the end-to-end process of preparing an argumentative essay for a debate, which covers the tasks of claim and evidence identification (Task 1 ED), evidence convincingness ranking (Task 2 ECR), argumentative essay summarisation and human preference ranking (Task 3 ASR) and metric learning for automated evaluation of resulting essays, based on human feedback along argument quality dimensions (Task 4 SQE). Our dataset contains 14k examples of claims that are fully annotated with the various properties supporting the aforementioned tasks. We evaluate multiple generative baselines for each of these tasks, including representative LLMs. We find, that while they show promising results on individual tasks in our benchmark, their end-to-end performance on all four tasks in succession deteriorates significantly, both in automated measures as well as in human-centred evaluation. This challenge presented by our proposed dataset motivates future research on end-to-end argument mining and summarisation. The repository of this project is available at https://github.com/HaoBytes/ArgSum-Datatset |
| title | Which Side Are You On? A Multi-task Dataset for End-to-End Argument Summarisation and Evaluation |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2406.03151 |