ArgMiner: End-to-End Argument Mining

Author(s): Yousef Nami

Originally published on Towards AI.

A PyTorch-based package for processing, augmenting, training, and performing inference on SOTA Argument Mining datasets

A pictorial representation of the task of Argument Mining

Argument Mining (AM) is the task of extracting argument components from text, typically as part of Automated Writing Evaluation systems. This is a very hot and exciting field in NLP. In the most basic terms, a good AM model takes a raw piece of text and correctly labels the sequences within it as the argument components that they belong (this is shown pictorially in the cover photo). While historically this problem was treated as a semantic segmentation problem, state-of-the-art (SOTA) AM techniques treat it as a Named Entity Recognition (NER) problem on… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI