Abstractive vs. Extractive Summarization: An Experimental Review
Text summarization is a subtask of natural language processing referring to the automatic creation of a concise and fluent summary that captures the main ideas and topics from one or multiple documents. Earlier literature surveys focus on extractive approaches, which rank the <i>top-n</i>...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/13/7620 |
| _version_ | 1797592105746432000 |
|---|---|
| author | Nikolaos Giarelis Charalampos Mastrokostas Nikos Karacapilidis |
| author_facet | Nikolaos Giarelis Charalampos Mastrokostas Nikos Karacapilidis |
| author_sort | Nikolaos Giarelis |
| collection | DOAJ |
| description | Text summarization is a subtask of natural language processing referring to the automatic creation of a concise and fluent summary that captures the main ideas and topics from one or multiple documents. Earlier literature surveys focus on extractive approaches, which rank the <i>top-n</i> most important sentences in the input document and then combine them to form a summary. As argued in the literature, the summaries of these approaches do not have the same lexical flow or coherence as summaries that are manually produced by humans. Newer surveys elaborate abstractive approaches, which generate a summary with potentially new phrases and sentences compared to the input document. Generally speaking, contrary to the extractive approaches, the abstractive ones create summaries that are more similar to those produced by humans. However, these approaches still lack the contextual representation needed to form fluent summaries. Recent advancements in deep learning and pretrained language models led to the improvement of many natural language processing tasks, including abstractive summarization. Overall, these surveys do not present a comprehensive evaluation framework that assesses the aforementioned approaches. Taking the above into account, the contribution of this survey is fourfold: (i) we provide a comprehensive survey of the state-of-the-art approaches in text summarization; (ii) we conduct a comparative evaluation of these approaches, using well-known datasets from the related literature, as well as popular evaluation scores such as <i>ROUGE-1, ROUGE-2, ROUGE-L, ROUGE-LSUM, BLEU-1, BLEU-2</i> and <i>SACREBLEU</i>; (iii) we report on insights gained on various aspects of the text summarization process, including existing approaches, datasets and evaluation methods, and we outline a set of open issues and future research directions; (iv) we upload the datasets and the code used in our experiments in a public repository, aiming to increase the reproducibility of this work and facilitate future research in the field. |
| first_indexed | 2024-03-11T01:46:44Z |
| format | Article |
| id | doaj.art-0b2baba401334afc9e1bac6506a30aa5 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T01:46:44Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-0b2baba401334afc9e1bac6506a30aa52023-11-18T16:09:03ZengMDPI AGApplied Sciences2076-34172023-06-011313762010.3390/app13137620Abstractive vs. Extractive Summarization: An Experimental ReviewNikolaos Giarelis0Charalampos Mastrokostas1Nikos Karacapilidis2Industrial Management and Information Systems Lab, Department of Mechanical Engineering and Aeronautics, University of Patras, 26504 Rio Patras, GreeceDepartment of Electrical and Computer Engineering, University of Patras, 26504 Rio Patras, GreeceIndustrial Management and Information Systems Lab, Department of Mechanical Engineering and Aeronautics, University of Patras, 26504 Rio Patras, GreeceText summarization is a subtask of natural language processing referring to the automatic creation of a concise and fluent summary that captures the main ideas and topics from one or multiple documents. Earlier literature surveys focus on extractive approaches, which rank the <i>top-n</i> most important sentences in the input document and then combine them to form a summary. As argued in the literature, the summaries of these approaches do not have the same lexical flow or coherence as summaries that are manually produced by humans. Newer surveys elaborate abstractive approaches, which generate a summary with potentially new phrases and sentences compared to the input document. Generally speaking, contrary to the extractive approaches, the abstractive ones create summaries that are more similar to those produced by humans. However, these approaches still lack the contextual representation needed to form fluent summaries. Recent advancements in deep learning and pretrained language models led to the improvement of many natural language processing tasks, including abstractive summarization. Overall, these surveys do not present a comprehensive evaluation framework that assesses the aforementioned approaches. Taking the above into account, the contribution of this survey is fourfold: (i) we provide a comprehensive survey of the state-of-the-art approaches in text summarization; (ii) we conduct a comparative evaluation of these approaches, using well-known datasets from the related literature, as well as popular evaluation scores such as <i>ROUGE-1, ROUGE-2, ROUGE-L, ROUGE-LSUM, BLEU-1, BLEU-2</i> and <i>SACREBLEU</i>; (iii) we report on insights gained on various aspects of the text summarization process, including existing approaches, datasets and evaluation methods, and we outline a set of open issues and future research directions; (iv) we upload the datasets and the code used in our experiments in a public repository, aiming to increase the reproducibility of this work and facilitate future research in the field.https://www.mdpi.com/2076-3417/13/13/7620text summarizationdeep learninglanguage modelsnatural language processingabstractive summarizationextractive summarization |
| spellingShingle | Nikolaos Giarelis Charalampos Mastrokostas Nikos Karacapilidis Abstractive vs. Extractive Summarization: An Experimental Review Applied Sciences text summarization deep learning language models natural language processing abstractive summarization extractive summarization |
| title | Abstractive vs. Extractive Summarization: An Experimental Review |
| title_full | Abstractive vs. Extractive Summarization: An Experimental Review |
| title_fullStr | Abstractive vs. Extractive Summarization: An Experimental Review |
| title_full_unstemmed | Abstractive vs. Extractive Summarization: An Experimental Review |
| title_short | Abstractive vs. Extractive Summarization: An Experimental Review |
| title_sort | abstractive vs extractive summarization an experimental review |
| topic | text summarization deep learning language models natural language processing abstractive summarization extractive summarization |
| url | https://www.mdpi.com/2076-3417/13/13/7620 |
| work_keys_str_mv | AT nikolaosgiarelis abstractivevsextractivesummarizationanexperimentalreview AT charalamposmastrokostas abstractivevsextractivesummarizationanexperimentalreview AT nikoskaracapilidis abstractivevsextractivesummarizationanexperimentalreview |