Summarization, Simplification, and Generation: The Case of Patents

TL;DR

This survey reviews NLP techniques for patent summarization, simplification, and generation, highlighting unique challenges and recent advances, and emphasizing future research directions in this specialized domain.

Contribution

It is the first comprehensive survey focusing on generative NLP approaches specifically applied to patents, addressing their unique complexities.

Findings

Patents' unique language poses challenges for NLP models.

Recent generative methods have begun to address patent-specific tasks.

Identifies key research gaps and future directions in patent NLP.

Abstract

We survey Natural Language Processing (NLP) approaches to summarizing, simplifying, and generating patents' text. While solving these tasks has important practical applications - given patents' centrality in the R&D process - patents' idiosyncrasies open peculiar challenges to the current NLP state of the art. This survey aims at a) describing patents' characteristics and the questions they raise to the current NLP systems, b) critically presenting previous work and its evolution, and c) drawing attention to directions of research in which further work is needed. To the best of our knowledge, this is the first survey of generative approaches in the patent domain.