Abstract Meaning Representation for Multi-Document Summarization

Abstract

Generating an abstract from a collection of documents is a desirable capability for many real-world applications. However, abstractive approaches to multi-document summarization have not been thoroughly investigated. This paper studies the feasibility of using Abstract Meaning Representation (AMR), a semantic representation of natural language grounded in linguistic theory, as a form of content representation. Our approach condenses source documents to a set of summary graphs following the AMR formalism. The summary graphs are then transformed to a set of summary sentences in a surface realization step. The framework is fully data-driven and flexible. Each component can be optimized independently using small-scale, in-domain training data. We perform experiments on benchmark summarization datasets and report promising results. We also describe opportunities and challenges for advancing this line of research.

13 pages

References in corpus (9)

• A Deep Reinforced Model for Abstractive Summarization
• SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents
• Selective Encoding for Abstractive Sentence Summarization
• Faithful to the Original: Fact Aware Neural Abstractive Summarization
• Structure-Infused Copy Mechanisms for Abstractive Summarization
• Distraction-Based Neural Networks for Document Summarization
• Controlling Output Length in Neural Encoder-Decoders
• AMR-to-text Generation with Synchronous Node Replacement Grammar
• AMR-to-text generation as a Traveling Salesman Problem

Cited by in corpus (9)

• A Survey of Knowledge-Enhanced Text Generation
• Graph Neural Networks for Natural Language Processing: A Survey
• Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization
• Generating Representative Headlines for News Stories
• Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering
• Enhancing AMR-to-Text Generation with Dual Graph Representations
• An analysis of document graph construction methods for AMR summarization
• Online Back-Parsing for AMR-to-Text Generation
• WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipedia