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.
Publication Date
1-1-2018
Publication Title
COLING 2018 - 27th International Conference on Computational Linguistics, Proceedings
Number of Pages
1178-1190
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
Copyright Status
Unknown
Socpus ID
85055608122 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85055608122
STARS Citation
Liao, Kexin; Lebanoff, Logan; and Liu, Fei, "Abstract Meaning Representation For Multi-Document Summarization" (2018). Scopus Export 2015-2019. 8886.
https://stars.library.ucf.edu/scopus2015/8886