Can You Give Me a Reason?: Argument-inducing Online Forum by Argument Mining
| Autor: | Gaku Morio, Tomoyuki Tatsumi, Takaki Yasui, Makiko Ida, Katsuhide Fujita, Kosui Iwasa |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
World Wide Web
Online discussion Computer science Argument 020204 information systems Argument mining 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing 02 engineering and technology Online forum Code (semiotics) Argumentation theory |
| Zdroj: | WWW |
| Popis: | This demonstration paper presents an argument-inducing online forum that stimulates participants with lack of premises for their claim in online discussions. The proposed forum provides its participants the following two subsystems: (1) Argument estimator for online discussions automatically generates a visualization of the argument structures in posts based on argument mining. The forum indicates structures such as claim-premise relations in real time by exploiting a state-of-the-art deep learning model. (2) Argument-inducing agent for online discussion (AIAD) automatically generates a reply post based on the argument estimator requesting further reasons to improve the argumentation of participants. Our experimental discussion demonstrates that the argument estimator can detect the argument structures from online discussions, and AIAD can induce premises from the participants. To the best of our knowledge, our argument-inducing online forum is the first approach to either visualize or request a real-time argument for online discussions. Our forum can be used to collect and induce claim-reasons pairs rather than only opinions to understand various lines of reasoning in online arguments such as civic discussions, online debates, and education objectives. The argument estimator code is available at https://github.com/EdoFrank/EMNLP2018-ArgMining-Morio and the demonstration video is available at https://youtu.be/T9fNJfneQV8. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|