Is Everything in Order? A Simple Way to Order Sentences
This addresses the problem of organizing shuffled sentences into coherent text for evaluating machine understanding of causal and temporal relations, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the sentence ordering task by formulating it as a conditional text-to-marker generation problem, introducing Reorder-BART (Re-BART) which achieves state-of-the-art performance across 7 datasets in Perfect Match Ratio (PMR) and Kendall's tau (τ), including in zero-shot settings.
The task of organizing a shuffled set of sentences into a coherent text has been used to evaluate a machine's understanding of causal and temporal relations. We formulate the sentence ordering task as a conditional text-to-marker generation problem. We present Reorder-BART (Re-BART) that leverages a pre-trained Transformer-based model to identify a coherent order for a given set of shuffled sentences. The model takes a set of shuffled sentences with sentence-specific markers as input and generates a sequence of position markers of the sentences in the ordered text. Re-BART achieves the state-of-the-art performance across 7 datasets in Perfect Match Ratio (PMR) and Kendall's tau ($τ$). We perform evaluations in a zero-shot setting, showcasing that our model is able to generalize well across other datasets. We additionally perform several experiments to understand the functioning and limitations of our framework.