Improving argument overlap for proposition-based summarisation

Conference Object
Change log
Fang, Y 

We present improvements to our incremental proposition-based summariser, which is inspired by Kintsch and van Dijk's (1978) text comprehension model. Argument overlap is a central concept in this summariser. Our new model replaces the old overlap method based on distributional similarity with one based on lexical chains. We evaluate on a new corpus of 124 summaries of educational texts, and show that our new system outperforms the old method and several stateof-the-art non-proposition-based summarisers. The experiment also verifies that the incremental nature of memory cycles is beneficial in itself, by comparing it to a non-incremental algorithm using the same underlying information.

Journal Title
54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers
Conference Name
ACL 2016: 54th Annual Meeting of the Association for Computational Linguistics
Journal ISSN
Volume Title
Association for Computational Linguistics
The CSC Cambridge International Scholarship for the first author is gratefully acknowledged.