Identification of Propositional and Illocutionary Relations

annotate dialogue based on the inference anchoring theory (IAT). The task can be split into two parts, identification of propositional relations and identification of illocutionary relations. We propose a pipelined system made up of three parts: (1) locutionary– propositions relation detection, (2) propositional relations detection, and (3) illocutionary relations identification. We fine-tune models independently for each step, and combine at the end for the final system

The main goal of this task is to construct a dialogue graph under the IAT format. The input of this task is an unfinished graph that contains L-nodes (Locutions), I-nodes (Propositions), and TA-nodes (Direct Transition). The L-nodes are all connected in the order they were uttered in, with a TA-node between each L-node.