Attentional Extractive Summarization
In this work, a general theoretical framework for extractive summarization is proposed—the Attentional Extractive Summarization framework. Although abstractive approaches are generally used in text summarization today, extractive methods can be especially suitable for some applications, and they can...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/3/1458 |
| _version_ | 1827760485689196544 |
|---|---|
| author | José Ángel González Encarna Segarra Fernando García-Granada Emilio Sanchis Lluís-F. Hurtado |
| author_facet | José Ángel González Encarna Segarra Fernando García-Granada Emilio Sanchis Lluís-F. Hurtado |
| author_sort | José Ángel González |
| collection | DOAJ |
| description | In this work, a general theoretical framework for extractive summarization is proposed—the Attentional Extractive Summarization framework. Although abstractive approaches are generally used in text summarization today, extractive methods can be especially suitable for some applications, and they can help with other tasks such as Text Classification, Question Answering, and Information Extraction. The proposed approach is based on the interpretation of the attention mechanisms of hierarchical neural networks, which compute document-level representations of documents and summaries from sentence-level representations, which, in turn, are computed from word-level representations. The models proposed under this framework are able to automatically learn relationships among document and summary sentences, without requiring Oracle systems to compute the reference labels for each sentence before the training phase. These relationships are obtained as a result of a binary classification process, the goal of which is to distinguish correct summaries for documents. Two different systems, formalized under the proposed framework, were evaluated on the CNN/DailyMail and the NewsRoom corpora, which are some of the reference corpora in the most relevant works on text summarization. The results obtained during the evaluation support the adequacy of our proposal and suggest that there is still room for the improvement of our attentional framework. |
| first_indexed | 2024-03-11T09:53:08Z |
| format | Article |
| id | doaj.art-96f730525c8845559e28111c4fe10575 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T09:53:08Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-96f730525c8845559e28111c4fe105752023-11-16T16:05:45ZengMDPI AGApplied Sciences2076-34172023-01-01133145810.3390/app13031458Attentional Extractive SummarizationJosé Ángel González0Encarna Segarra1Fernando García-Granada2Emilio Sanchis3Lluís-F. Hurtado4Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Politècnica de València, 46022 Valencia, SpainValencian Research Institute for Artificial Intelligence (VRAIN), Universitat Politècnica de València, 46022 Valencia, SpainValencian Research Institute for Artificial Intelligence (VRAIN), Universitat Politècnica de València, 46022 Valencia, SpainValencian Research Institute for Artificial Intelligence (VRAIN), Universitat Politècnica de València, 46022 Valencia, SpainValencian Research Institute for Artificial Intelligence (VRAIN), Universitat Politècnica de València, 46022 Valencia, SpainIn this work, a general theoretical framework for extractive summarization is proposed—the Attentional Extractive Summarization framework. Although abstractive approaches are generally used in text summarization today, extractive methods can be especially suitable for some applications, and they can help with other tasks such as Text Classification, Question Answering, and Information Extraction. The proposed approach is based on the interpretation of the attention mechanisms of hierarchical neural networks, which compute document-level representations of documents and summaries from sentence-level representations, which, in turn, are computed from word-level representations. The models proposed under this framework are able to automatically learn relationships among document and summary sentences, without requiring Oracle systems to compute the reference labels for each sentence before the training phase. These relationships are obtained as a result of a binary classification process, the goal of which is to distinguish correct summaries for documents. Two different systems, formalized under the proposed framework, were evaluated on the CNN/DailyMail and the NewsRoom corpora, which are some of the reference corpora in the most relevant works on text summarization. The results obtained during the evaluation support the adequacy of our proposal and suggest that there is still room for the improvement of our attentional framework.https://www.mdpi.com/2076-3417/13/3/1458siamese neural networkshierarchical neural networksattention mechanismsextractive summarization |
| spellingShingle | José Ángel González Encarna Segarra Fernando García-Granada Emilio Sanchis Lluís-F. Hurtado Attentional Extractive Summarization Applied Sciences siamese neural networks hierarchical neural networks attention mechanisms extractive summarization |
| title | Attentional Extractive Summarization |
| title_full | Attentional Extractive Summarization |
| title_fullStr | Attentional Extractive Summarization |
| title_full_unstemmed | Attentional Extractive Summarization |
| title_short | Attentional Extractive Summarization |
| title_sort | attentional extractive summarization |
| topic | siamese neural networks hierarchical neural networks attention mechanisms extractive summarization |
| url | https://www.mdpi.com/2076-3417/13/3/1458 |
| work_keys_str_mv | AT joseangelgonzalez attentionalextractivesummarization AT encarnasegarra attentionalextractivesummarization AT fernandogarciagranada attentionalextractivesummarization AT emiliosanchis attentionalextractivesummarization AT lluisfhurtado attentionalextractivesummarization |