Evidence-Aware Inferential Text Generation with Vector Quantised Variational AutoEncoder

TL;DR

This paper introduces an evidence-aware text generation model using a Vector Quantised Variational Autoencoder, which improves inferential text generation by incorporating relevant evidence from large corpora, outperforming existing methods.

Contribution

It proposes a novel evidence-guided inferential text generation approach with discrete representations that enhance evidence selection and rationale uncovering.

Findings

Achieves state-of-the-art results on Event2Mind and ATOMIC datasets.

Effectively selects relevant evidence for diverse inferential texts.

Uncovers rationales behind generated inferences.

Abstract

Generating inferential texts about an event in different perspectives requires reasoning over different contexts that the event occurs. Existing works usually ignore the context that is not explicitly provided, resulting in a context-independent semantic representation that struggles to support the generation. To address this, we propose an approach that automatically finds evidence for an event from a large text corpus, and leverages the evidence to guide the generation of inferential texts. Our approach works in an encoder-decoder manner and is equipped with a Vector Quantised-Variational Autoencoder, where the encoder outputs representations from a distribution over discrete variables. Such discrete representations enable automatically selecting relevant evidence, which not only facilitates evidence-aware generation, but also provides a natural way to uncover rationales behind the generation. Our approach provides state-of-the-art performance on both Event2Mind and ATOMIC datasets. More importantly, we find that with discrete representations, our model selectively uses evidence to generate different inferential texts.