GeSERA: General-domain Summary Evaluation by Relevance Analysis

Jessica López Espejel, Gaël de Chalendar, Jorge Garcia Flores, Thierry Charnois, Ivan Vladimir Meza Ruiz


Abstract
We present GeSERA, an open-source improved version of SERA for evaluating automatic extractive and abstractive summaries from the general domain. SERA is based on a search engine that compares candidate and reference summaries (called queries) against an information retrieval document base (called index). SERA was originally designed for the biomedical domain only, where it showed a better correlation with manual methods than the widely used lexical-based ROUGE method. In this paper, we take out SERA from the biomedical domain to the general one by adapting its content-based method to successfully evaluate summaries from the general domain. First, we improve the query reformulation strategy with POS Tags analysis of general-domain corpora. Second, we replace the biomedical index used in SERA with two article collections from AQUAINT-2 and Wikipedia. We conduct experiments with TAC2008, TAC2009, and CNNDM datasets. Results show that, in most cases, GeSERA achieves higher correlations with manual evaluation methods than SERA, while it reduces its gap with ROUGE for general-domain summary evaluation. GeSERA even surpasses ROUGE in two cases of TAC2009. Finally, we conduct extensive experiments and provide a comprehensive study of the impact of human annotators and the index size on summary evaluation with SERA and GeSERA.
Anthology ID:
2021.ranlp-1.98
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
Month:
September
Year:
2021
Address:
Held Online
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
856–867
Language:
URL:
https://aclanthology.org/2021.ranlp-1.98
DOI:
Bibkey:
Cite (ACL):
Jessica López Espejel, Gaël de Chalendar, Jorge Garcia Flores, Thierry Charnois, and Ivan Vladimir Meza Ruiz. 2021. GeSERA: General-domain Summary Evaluation by Relevance Analysis. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 856–867, Held Online. INCOMA Ltd..
Cite (Informal):
GeSERA: General-domain Summary Evaluation by Relevance Analysis (López Espejel et al., RANLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.ranlp-1.98.pdf