Toward Diverse Precondition Generation

TL;DR

This paper introduces DiP, a system for generating diverse precondition events for target events in discourse, addressing the challenge of multiple possible preconditions without requiring diverse training data.

Contribution

DiP is a novel generative framework that automatically produces diverse preconditions using control codes, improving over standard seq2seq models.

Findings

DiP significantly increases the diversity of generated preconditions.

DiP produces more preconditions per target event compared to baselines.

DiP outperforms existing methods in generating unique and relevant preconditions.

Abstract

Language understanding must identify the logical connections between events in a discourse, but core events are often unstated due to their commonsense nature. This paper fills in these missing events by generating precondition events. Precondition generation can be framed as a sequence-to-sequence problem: given a target event, generate a possible precondition. However, in most real-world scenarios, an event can have several preconditions, requiring diverse generation -- a challenge for standard seq2seq approaches. We propose DiP, a Diverse Precondition generation system that can generate unique and diverse preconditions. DiP uses a generative process with three components -- an event sampler, a candidate generator, and a post-processor. The event sampler provides control codes (precondition triggers) which the candidate generator uses to focus its generation. Unlike other conditional generation systems, DiP automatically generates control codes without training on diverse examples. Analysis against baselines reveals that DiP improves the diversity of preconditions significantly while also generating more preconditions.