Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference

TL;DR

This paper introduces a novel NLI model that leverages discourse markers and reinforcement learning to enhance sentence relationship inference, achieving state-of-the-art results on multiple datasets.

Contribution

It proposes integrating discourse markers into NLI models and employing reinforcement learning for optimization, which is a new approach in this domain.

Findings

Achieves state-of-the-art performance on large-scale NLI datasets.

Utilizes discourse markers to improve sentence representation.

Employs reinforcement learning to optimize the model effectively.

Abstract

Natural Language Inference (NLI), also known as Recognizing Textual Entailment (RTE), is one of the most important problems in natural language processing. It requires to infer the logical relationship between two given sentences. While current approaches mostly focus on the interaction architectures of the sentences, in this paper, we propose to transfer knowledge from some important discourse markers to augment the quality of the NLI model. We observe that people usually use some discourse markers such as "so" or "but" to represent the logical relationship between two sentences. These words potentially have deep connections with the meanings of the sentences, thus can be utilized to help improve the representations of them. Moreover, we use reinforcement learning to optimize a new objective function with a reward defined by the property of the NLI datasets to make full use of the labels information. Experiments show that our method achieves the state-of-the-art performance on several large-scale datasets.