Generating Contradictory, Neutral, and Entailing Sentences

TL;DR

This paper introduces a novel adversarial approach for generating sentences conditioned on input sentences and logical inference labels, improving diversity and quality in NLP tasks.

Contribution

It proposes a new method to generate diverse sentences conditioned on logical inference labels using adversarial training, advancing NLP sentence generation techniques.

Findings

Model improves sentence diversity and quality

BLEU scores indicate better alignment with target sentences

Framework offers clear pathways for enhancement

Abstract

Learning distributed sentence representations remains an interesting problem in the field of Natural Language Processing (NLP). We want to learn a model that approximates the conditional latent space over the representations of a logical antecedent of the given statement. In our paper, we propose an approach to generating sentences, conditioned on an input sentence and a logical inference label. We do this by modeling the different possibilities for the output sentence as a distribution over the latent representation, which we train using an adversarial objective. We evaluate the model using two state-of-the-art models for the Recognizing Textual Entailment (RTE) task, and measure the BLEU scores against the actual sentences as a probe for the diversity of sentences produced by our model. The experiment results show that, given our framework, we have clear ways to improve the quality and diversity of generated sentences.