Abstract Meaning Representation for Multi-Document Summarization
This addresses the problem of generating abstracts from document collections for real-world applications, but it is incremental as it builds on existing AMR methods.
The paper tackled multi-document summarization by using Abstract Meaning Representation (AMR) to condense documents into summary graphs and generate sentences, reporting promising results on benchmark datasets.
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.