Dual Inference for Improving Language Understanding and Generation

TL;DR

This paper introduces a dual inference approach that leverages the relationship between natural language understanding and generation to improve performance without retraining large models, demonstrated on benchmark datasets.

Contribution

It proposes a novel inference-stage method exploiting NLU and NLG duality, avoiding the need for retraining large models.

Findings

Effective in both NLU and NLG tasks

Improves performance without retraining models

Shows strong results on benchmark datasets

Abstract

Natural language understanding (NLU) and Natural language generation (NLG) tasks hold a strong dual relationship, where NLU aims at predicting semantic labels based on natural language utterances and NLG does the opposite. The prior work mainly focused on exploiting the duality in model training in order to obtain the models with better performance. However, regarding the fast-growing scale of models in the current NLP area, sometimes we may have difficulty retraining whole NLU and NLG models. To better address the issue, this paper proposes to leverage the duality in the inference stage without the need of retraining. The experiments on three benchmark datasets demonstrate the effectiveness of the proposed method in both NLU and NLG, providing the great potential of practical usage.