Improving argument overlap for proposition-based summarisation
54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers
ACL 2016: 54th Annual Meeting of the Association for Computational Linguistics
Association for Computational Linguistics
MetadataShow full item record
Fang, Y., & Teufel, S. (2016). Improving argument overlap for proposition-based summarisation. 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers, 479-485. http://aclanthology.info/papers/P16-2078/improving-argument-overlap-for-proposition-based-summarisation
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.
The CSC Cambridge International Scholarship for the first author is gratefully acknowledged.
External link: http://aclanthology.info/papers/P16-2078/improving-argument-overlap-for-proposition-based-summarisation
This record's URL: https://www.repository.cam.ac.uk/handle/1810/267185
Attribution 4.0 International
Licence URL: http://creativecommons.org/licenses/by/4.0/