Concept-Map-Based Multi-Document Summarization using Concept Coreference Resolution and Global Importance Optimization

Tobias Falke, Christian M. Meyer, Iryna Gurevych
2017 International Joint Conference on Natural Language Processing  
Concept-map-based multi-document summarization is a variant of traditional summarization that produces structured summaries in the form of concept maps. In this work, we propose a new model 1 for the task that addresses several issues in previous methods. It learns to identify and merge coreferent concepts to reduce redundancy, determines their importance with a strong supervised model and finds an optimal summary concept map via integer linear programming. It is also computationally more
more » ... ent than previous methods, allowing us to summarize larger document sets. We evaluate the model on two datasets, finding that it outperforms several approaches from previous work.
dblp:conf/ijcnlp/FalkeMG17 fatcat:4zya63huavahtdaytu6j4wb4qa