Transfer Learning of Lexical Semantic Families for Argumentative Discourse Units Identification
This addresses the challenge of enhancing argument mining for NLP researchers, but it is incremental as it builds on existing transfer learning techniques.
The study investigated whether pre-trained language models from different lexical semantic families improve the identification of argumentative discourse units in argument mining, finding that transfer learning helps but current methods may not fully leverage commonsense knowledge from these families.
Argument mining tasks require an informed range of low to high complexity linguistic phenomena and commonsense knowledge. Previous work has shown that pre-trained language models are highly effective at encoding syntactic and semantic linguistic phenomena when applied with transfer learning techniques and built on different pre-training objectives. It remains an issue of how much the existing pre-trained language models encompass the complexity of argument mining tasks. We rely on experimentation to shed light on how language models obtained from different lexical semantic families leverage the performance of the identification of argumentative discourse units task. Experimental results show that transfer learning techniques are beneficial to the task and that current methods may be insufficient to leverage commonsense knowledge from different lexical semantic families.