Understanding and Detecting Supporting Arguments of Diverse Types
This work addresses argument detection for debate or fact-checking applications, but it is incremental as it builds on existing ranking methods with type-based features.
The paper tackles the problem of detecting sentence-level supporting arguments from documents for user-specified claims, using a manually labeled dataset from an online debate website with argument types (study, factual, opinion, reasoning). The result shows that a LambdaMART ranker using features informed by argument types yields better performance than without type information.
We investigate the problem of sentence-level supporting argument detection from relevant documents for user-specified claims. A dataset containing claims and associated citation articles is collected from online debate website idebate.org. We then manually label sentence-level supporting arguments from the documents along with their types as study, factual, opinion, or reasoning. We further characterize arguments of different types, and explore whether leveraging type information can facilitate the supporting arguments detection task. Experimental results show that LambdaMART (Burges, 2010) ranker that uses features informed by argument types yields better performance than the same ranker trained without type information.