Beyond Generative Artificial Intelligence: Roadmap for Natural Language Generation

TL;DR

This paper reviews recent NLG surveys to identify gaps and future directions in natural language generation, especially in the context of advanced LLMs like GPT-4 and ChatGPT.

Contribution

It provides a research roadmap highlighting unresolved challenges and future research avenues in NLG amidst the rise of large language models.

Findings

Identifies key areas where LLMs still underperform in NLG tasks.

Highlights gaps in current NLG research addressed by recent surveys.

Suggests future research directions for advancing NLG with LLMs.

Abstract

Generative Artificial Intelligence has grown exponentially as a result of Large Language Models (LLMs). This has been possible because of the impressive performance of deep learning methods created within the field of Natural Language Processing (NLP) and its subfield Natural Language Generation (NLG), which is the focus of this paper. Within the growing LLM family are the popular GPT-4, Bard and more specifically, tools such as ChatGPT have become a benchmark for other LLMs when solving most of the tasks involved in NLG research. This scenario poses new questions about the next steps for NLG and how the field can adapt and evolve to deal with new challenges in the era of LLMs. To address this, the present paper conducts a review of a representative sample of surveys recently published in NLG. By doing so, we aim to provide the scientific community with a research roadmap to identify which NLG aspects are still not suitably addressed by LLMs, as well as suggest future lines of research that should be addressed going forward.