Extractive single-document summarization using adaptive binary constrained multi-objective differential evaluation

Dipanwita Debnath1, Ranjita Das1, Partha Pakray2, Ruzina Laskar1
1National Institute of Technology Mizoram, Aizawl, India
2National Institute of Technology Silchar, Silchar, India

Tóm tắt

The incredible growth of the Internet has enhanced the research and development of automatic text summarization. Several approaches were proposed in the literature for automatic text summarization using a Multi-objective optimization (MOO) framework. But, still, it is difficult to decide which feature set and objective functions are best suited for the summarization task. Improving these objective functions along with the suitable optimization framework can bring diversity among the solutions and convergence towards genuine Pareto optimal fronts. So, it can be fascinating to prospect other proficient techniques that can further improve the performance of the automatic summarization process. This work proposes an adaptive binary constrained differential evolution (ABCDE) technique in the MOO framework for solving the summarization problem. The implemented system significantly outperformed various existing methods on ROUGE measures when evaluated on DUC 2001 and DUC 2002 data sets. Obtained results illustrate the supremacy of the proposed approach in terms of ROUGE scores, readability, and relevancy.

Tài liệu tham khảo

Radev DR, Hovy E, McKeown K (2002) Introduction to the special issue on summarization. Comput Linguist 28(4):399–408 Maybury M (1999) Advances in automatic text summarization. MIT Press, Cambridge Alguliev RM, Aliguliyev RM (2005) Effective summarization method of text documents. In: The 2005 IEEE/WIC/ACM international conference on web intelligence (WI’05). IEEE, pp 264–271 Abbasi-ghalehtaki R, Khotanlou H, Esmaeilpour M (2016) Fuzzy evolutionary cellular learning automata model for text summarization. Swarm Evol Comput 30:11–26 Song W, Choi LC, Park SC, Ding XF (2011) Fuzzy evolutionary optimization modeling and its applications to unsupervised categorization and extractive summarization. Expert Syst Appl 38(8):9112–9121 Vázquez E, Arnulfo Garcia-Hernandez R, Ledeneva Y (2018) Sentence features relevance for extractive text summarization using genetic algorithms. J Intell Fuzzy Syst 35(1):353–365 Debnath D, Das R, Pakray P (2020) Extractive single document summarization using an archive-based micro genetic-2. In: 2020 7th international conference on soft computing and machine intelligence (ISCMI). IEEE, pp 244–248 Alguliyev RM, Aliguliyev RM, Isazade NR, Abdi A, Idris N (2019) Cosum: text summarization based on clustering and optimization. Expert Syst 36(1):e12340 Saini N, Saha S, Jangra A, Bhattacharyya P (2019) Extractive single document summarization using multi-objective optimization: exploring self-organized differential evolution, grey wolf optimizer and water cycle algorithm. Knowl Based Syst 164:45–67 Storn R, Price K (1996) Minimizing the real functions of the icec’96 contest by differential evolution. In: Proceedings of IEEE international conference on evolutionary computation. IEEE, pp 842–844 Suresh K, Kundu D, Ghosh S, Das S, Abraham A (2009) Data clustering using multi-objective differential evolution algorithms. Fund Inform 97(4):381–403 Das S, Abraham A, Konar A (2007) Automatic clustering using an improved differential evolution algorithm. IEEE Trans Syst Man Cybern Part A Syst Hum 38(1):218–237 Zhang D, Wei B (2014) Comparison between differential evolution and particle swarm optimization algorithms. In: 2014 IEEE international conference on mechatronics and automation. IEEE, pp 239–244 Deb K, Pratap A, Agarwal S, Meyarivan T (2002) A fast and elitist multiobjective genetic algorithm: Nsga-ii. IEEE Trans Evol Comput 6(2):182–197 Binwahlan MS, Salim N, Suanmali L (2009) Swarm based text summarization. In: 2009 international association of computer science and information technology-spring conference. IEEE, pp 145–150 Mirjalili S, Mirjalili SM, Lewis A (2014) Grey wolf optimizer. Adv Eng Softw 69:46–61 Eskandar H, Sadollah A, Bahreininejad A, Hamdi M (2012) Water cycle algorithm-a novel metaheuristic optimization method for solving constrained engineering optimization problems. Comput. Struct. 110:151–166 Saini N, Saha S, Chakraborty D, Bhattacharyya P (2019) Extractive single document summarization using binary differential evolution: optimization of different sentence quality measures. PLoS ONE 14(11):e0223477 Tiwari S, Fadel G, Deb K (2011) Amga2: improving the performance of the archive-based micro-genetic algorithm for multi-objective optimization. Eng Optim 43(4):377–401 Prasad R, Kulkarni U, Prasad J (2009) Machine learning in evolving connectionist text summarizer. Anti-counterfeiting Sec Identif Commun 2009:539–543 Luhn HP (1958) The automatic creation of literature abstracts. IBM J Res Dev 2(2):159–165 Baxendale PB (1958) Machine-made index for technical literature—an experiment. IBM J Res Dev 2(4):354–361 Edmundson HP (1969) New methods in automatic extracting. J ACM 16(2):264–285 Baralis E, Cagliero L, Fiori A, Garza P (2015) Mwi-sum: a multilingual summarizer based on frequent weighted itemsets. ACM Trans Inf Syst 34(1):1–35 Sutskever I, Vinyals O, Le QV, Sequence to sequence learning with neural networks, arXiv preprint arXiv:1409.3215 Cho K, Van Merriënboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y, Learning phrase representations using rnn encoder-decoder for statistical machine translation, arXiv preprint arXiv:1406.1078 Debnath D, Das R, Rafi S (2022) Sentiment-based abstractive text summarization using attention oriented lstm model. In: Intelligent data engineering and analytics. Springer, pp 199–208 James C, Mirella L (2010) Discourse constraints for document compression. Assoc Comput Linguist 36(3):411–441 Daumé III H, Marcu D (2002) A noisy-channel model for document compression. In: Proceedings of the 40th annual meeting of the association for computational linguistics (ACL), Philadelphia, July 2002. Association for Computational Linguistics, pp 449–456 Vinyals O, Le Q, A neural conversational model, arXiv preprint arXiv:1506.05869 Wan X (2010) Towards a unified approach to simultaneous single-document and multi-document summarizations. In: Proceedings of the 23rd international conference on computational linguistics (Coling 2010), pp 1137–1145 Mendoza M, Cobos C, León E (2015) Extractive single-document summarization based on global-best harmony search and a greedy local optimizer. In: Mexican international conference on artificial intelligence. Springer, pp 52–66 Mendoza M, Bonilla S, Noguera C, Cobos C, León E (2014) Extractive single-document summarization based on genetic operators and guided local search. Expert Syst Appl 41(9):4158–4169 Aliguliyev RM (2009) A new sentence similarity measure and sentence based extractive technique for automatic text summarization. Expert Syst Appl 36(4):7764–7772 Verma P, Verma A, Pal S (2022) An approach for extractive text summarization using fuzzy evolutionary and clustering algorithms. Appl Soft Comput 120:108670 Mojrian M, Mirroshandel SA (2021) A novel extractive multi-document text summarization system using quantum-inspired genetic algorithm: Mtsqiga. Expert Syst Appl 171:114555 Ehrgott M (2005) Multicriteria optimization, vol 491. Springer, Berlin Chica M, Bautista J, de Armas J (2019) Benefits of robust multiobjective optimization for flexible automotive assembly line balancing. Flex Serv Manuf J 31(1):75–103 Andoni A, Indyk P, Krauthgamer R (2008) Earth mover distance over high-dimensional spaces. In: SODA, vol 8. Citeseer, pp 343–352 Goldberg Y, Levy O, word2vec explained: deriving mikolov et al.’s negative-sampling word-embedding method, arXiv preprint arXiv:1402.3722 Chin-Yew L (2004) Rouge: a package for automatic evaluation of summaries. In: Text summarization branches out, pp 74–81 Saleh HH, Kadhim NJ, Attea B (2015) A genetic based optimization model for extractive multi-document text summarization. Iraqi J Sci 56(2):1489–1498