DAPrompt: Deterministic Assumption Prompt Learning for Event Causality Identification
This addresses the problem of identifying causal relations between events in text for natural language processing applications, representing an incremental improvement with a novel prompt design.
The paper tackled Event Causality Identification by proposing DAPrompt, a method that makes deterministic assumptions about causal relations and evaluates their rationality using pre-trained language models, achieving significant performance improvements over state-of-the-art algorithms on EventStoryLine and Causal-TimeBank corpora.
Event Causality Identification (ECI) aims at determining whether there is a causal relation between two event mentions. Conventional prompt learning designs a prompt template to first predict an answer word and then maps it to the final decision. Unlike conventional prompts, we argue that predicting an answer word may not be a necessary prerequisite for the ECI task. Instead, we can first make a deterministic assumption on the existence of causal relation between two events and then evaluate its rationality to either accept or reject the assumption. The design motivation is to try the most utilization of the encyclopedia-like knowledge embedded in a pre-trained language model. In light of such considerations, we propose a deterministic assumption prompt learning model, called DAPrompt, for the ECI task. In particular, we design a simple deterministic assumption template concatenating with the input event pair, which includes two masks as predicted events' tokens. We use the probabilities of predicted events to evaluate the assumption rationality for the final event causality decision. Experiments on the EventStoryLine corpus and Causal-TimeBank corpus validate our design objective in terms of significant performance improvements over the state-of-the-art algorithms.