A Survey : Neural Networks for AMR-to-Text

TL;DR

This survey reviews the development of neural network methods for converting Abstract Meaning Representation graphs into natural language text, highlighting recent progress, challenges, and future directions.

Contribution

It categorizes existing AMR-to-Text methods into five groups and details recent neural network advancements, including AMR reconstruction and decoder optimization.

Findings

Neural network-based methods dominate recent progress.

Transformer and pre-trained models improve generation quality.

Benchmark datasets and evaluation metrics are summarized.

Abstract

AMR-to-text is one of the key techniques in the NLP community that aims at generating sentences from the Abstract Meaning Representation (AMR) graphs. Since AMR was proposed in 2013, the study on AMR-to-Text has become increasingly prevalent as an essential branch of structured data to text because of the unique advantages of AMR as a high-level semantic description of natural language. In this paper, we provide a brief survey of AMR-to-Text. Firstly, we introduce the current scenario of this technique and point out its difficulties. Secondly, based on the methods used in previous studies, we roughly divided them into five categories according to their respective mechanisms, i.e., Rules-based, Seq-to-Seq-based, Graph-to-Seq-based, Transformer-based, and Pre-trained Language Model (PLM)-based. In particular, we detail the neural network-based method and present the latest progress of AMR-to-Text, which refers to AMR reconstruction, Decoder optimization, etc. Furthermore, we present the benchmarks and evaluation methods of AMR-to-Text. Eventually, we provide a summary of current techniques and the outlook for future research.