Extracting a Prototypical Argumentative Pattern in Financial Q&As

ACL ARR 2024 December Submission2046 Authors

Abstract:

Argumentative patterns are recurrent strategies adopted to pursue a definite communicative goal in a discussion. For instance, in Q&A exchanges during financial conference calls, a pattern called Request of Confirmation of Inference (ROCOI) helps streamline conversations by requesting explicit verification of inferences drawn from a statement.
Our work presents two ROCOI extraction approaches from interrogative units: sequence labeling and text-to-text generation. We experiment with multiple models for each task formulation to explore which models can effectively and robustly perform pattern extraction.
Results indicate that machine-based ROCOI extraction is an achievable task, though variation among metrics that are designed for different evaluation axes makes obtaining a clear picture difficult.
We find that overall, ROCOI extraction is performed best via sequence labeling (Token-level F1=0.31), though with ample room for improvement. We encourage future work to extend the study to new argumentative patterns.

Paper Type: Long

Research Area: Sentiment Analysis, Stylistic Analysis, and Argument Mining

Research Area Keywords: argument mining, argument schemes and reasoning

Contribution Types: Model analysis & interpretability, Approaches to low-resource settings, Data analysis

Languages Studied: English

Submission Number: 2046