Argument mining is an advanced technique of natural language processing (NLP) that aims to automatically identify and extract the structures of interpretation and reasoning expressed as arguments. Traditional methods face the challenge in argumentation mining while detecting long-range dependencies. Deep learning models utilize the deep neural network to capture the long-range dependencies in the controversial conservation due to their ability to process sequential data and handle huge datasets.
The attention mechanism is an additional neural architecture in deep learning to address the specific tasks which are unable to process using a deep neural network. A deep neural network with an attention mechanism helps identify the asymmetric relationship between the sentences in the controversial conversation. Deep neural network model with attention mechanism-based argument mining utilizes wider knowledge to perform reasoning and inference.
• Argument mining in natural language processing teaches machines about argumentative structures concerned with logical reasoning.
• The recent rapid surge in argumentation mining reflects the increasing demand for the automated extraction of deeper meaning from the abundant amounts of data in many real-world scenarios.
• Deep learning contributes to remarkable growth in the field of argumentation mining by performing advanced reasoning tasks over a large amount of data and supporting complex arguments.
• Attention mechanism-guided deep neural networks are employed for sentence, word, and topic level argumentation mining.
• Attention mechanism combined deep learning model for argument mining is the recent approach that yields better outcomes.
• More recently, multi-task learning infused with attentive neural networks is emerged to perform argument mining jointly.
• Scalability in argumentation mining systems remains an open research challenge that needs to be a focus in the future.