Studying the Effect of Syntactic Simplification on Text Summarization

Abstract

The need for automatic text summarization (ATS) is increased manifold in recent times due to the overwhelming growth of textual data available in electronic form. However, existing ATS systems suffer from two major shortcomings. Summarizers of extractive type, that is, the ones which select important sentences of the documents in their original form as the output, tend to copy some irrelevant or unimportant parts of the input text in the output summary. On the other hand, abstractive summarizers, that is, the ones that produce a gist of the limited size of the original document, often fail to include important contents in the generated summary. Simplification of the input texts before submitting them to the ATS system(s) may obliterate the above difficulties. The present work examines the effectiveness of simplification of input for five different known ATS systems. In this work, DEPSYM++ simplifier has been used for the above purpose, which carries out four different kinds of simplification on sentences of the input text corresponding to the presence of appositive clause, relative clause, conjoint clause, and passive voice. The results obtained are found to be very encouraging when experiments were carried out on three different gold data sets and under different evaluation metrics commonly used for performance evaluation for summarizers.

Keywords:

• Abstractive summary
• Relative clause
• ROUGE metric
• Syntactic simplification
• Text processing
• Text simplification
• Text summarization

Disclosure statement

No potential conflict of interest was reported by the author(s).

Notes

1 Code available at https://github.com/RakshaAg/DEPSYMSum.

2 https://pypi.org/project/sumy/.

3 https://huggingface.co/facebook/bart-large-cnn.

4 Dataset is available at https://github.com/RakshaAg/DEPSYMSum.

5 bert-base-uncased.

6 Except recall for DUC.

Additional information

Funding

Raksha Agarwal acknowledges Council of Scientific and Industrial Research (CSIR), India, for supporting the research [grant no: SPM-06/086(0267)/2018-EMR-I].

Notes on contributors

Niladri Chatterjee

Niladri Chatterjee is the Chair Professor of Artificial Intelligence in IIT Delhi. He is a professor of Statistics and Computer Science in the Department of Mathematics, IIT Delhi, School of IT and School of AI of IIT Delhi. His primary research areas are Artificial Intelligence, Natural Language Processing, Big Data Analytics, Statistical Modelling. His association with IIT Delhi has been more than 22 years. Prior to that, he had worked as a lecturer in University College London, and a computer engineer at Indian Statistical Institute, Calcutta. He has been a visiting professor in Department of Informatics, University of Pisa, Italy. He has supervised ten Ph.Ds. and over a hundred master’s thesis in Mathematics and Computing.

Raksha Agarwal

Raksha Agarwal is a PhD scholar in the Department of Mathematics, IIT Delhi. Her primary research areas are Natural Language Processing and Machine Learning, with focus on abstractive text summarization. She has done master of science in mathematics from IIT Delhi and bachelor of science in mathematics from the University of Delhi. She is the recipient of Shyama Prasad Mukherjee Fellowship awarded by the Council of Scientific and Industrial Research, India.Email: [email protected]