We present TARGER, an open source neural argument mining framework for tagging arguments in free input texts and for keyword-based retrieval of arguments from an argument-tagged web-scale corpus. The currently available models are pre-trained on three recent argument mining datasets and enable the use of neural argument mining without any reproducibility effort on the user's side. The open source code ensures portability to other domains and use cases, such as an application to search engine ranking that we also describe shortly.

We tackle the tasks of automatically identifying comparative sentences and categorizing the intended preference (e.g., "Python has better NLP libraries than MATLAB" → Python, better, MATLAB). To this end, we manually annotate 7,199 sentences for 217 distinct target item pairs from several domains (27% of the sentences contain an oriented comparison in the sense of "better" or "worse"). A gradient boosting model based on pre-trained sentence embeddings reaches an F1 score of 85% in our experimental evaluation. The model can be used to extract comparative sentences for pro/con argumentation in comparative / argument search engines or debating technologies.

No abstract

Technologies for argument mining and argumentation processing are maturing continuously, giving rise to the idea of retrieving arguments in search scenarios. We introduce Touché, the first lab on Argument Retrieval featuring two subtasks: (1) the retrieval of arguments from a focused debate collection to support argumentative conversations, and (2) the retrieval of arguments from a generic web crawl to answer comparative questions with argumentative results. The goal of this lab is to perform an evaluation of various strategies to retrieve argumentative information from the web content. In this paper, we describe the setting of each subtask: the motivation, the data, and the evaluation methodology.

No abstract