Abstractive Document Summarization via Neural Model with Joint Attention

Hou, Liwei; Hu, Po; Bei, Chao

doi:10.1007/978-3-319-73618-1_28

Cited by 30 publications

(22 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These algorithms find similar comparison statements and combine them to generate the abstractive summary [52]. Similar sentences are represented by a tree.…”

Section: ) Methods Based On Treesmentioning

confidence: 99%

“…Dependency trees are the most frequently used tree-form representations for text. Trees are managed through pruning, linearization (converting trees to strings), and other methods [52]. The method's advantages include enhanced quality generated summaries since language generators provide fewer redundant and fluent summaries [52]It is not feasible to discern relationships between sentences without first locating common terms.…”

Section: ) Methods Based On Treesmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Review of Arabic Text Summarization

et al. 2022

View full text Add to dashboard Cite

The explosion of online and offline data has changed how we gather, evaluate, and understand data. It is frequently difficult and time-consuming to comprehend large text documents and extract crucial information from them. Text summarization techniques address the mentioned problems by compressing long texts while retaining their essential contents. These techniques rely on the fast delivery of filtered, high-quality content to their users. Due to the massive amounts of data generated by technology and various sources, automated text summarization of large-scale data is challenging. There are three types of automatic text summarization techniques: extractive, abstractive, and hybrid. Regardless of these previous techniques, the generated summaries are a long way from the summarization produced by human experts. Although Arabic is a widely spoken language that is frequently used for content sharing on the web, Arabic text summarization of Arabic content is limited and still immature because of several problems, including the Arabic language's morphological structure, the variety of dialects, and the lack of adequate data sources. This paper reviews text summarization approaches and recent deep learning models for this approach. Additionally, it focuses on existing datasets for these approaches, which are also reviewed, along with their characteristics and limitations. The most often used metrics for summarization quality evaluation are ROUGE1, ROUGE2, ROUGE L, and Bleu. The challenges that are encountered during Arabic text summarizing methods and approaches and the solutions proposed in each approach are analyzed. Many Arabic text summarization methods have problems, such as the lack of golden tokens during testing, being out of vocabulary (OOV) words, repeating summary sentences, lack of standard systematic methodologies and architectures, and the complexity of the Arabic language. Finally, providing the required corpora, improving evaluation using semantic representations, the lack of using rouge metrics in abstractive text summarization, and using recent deep learning models to adopt them in Arabic summarization studies is an essential demand.

show abstract

“…These algorithms find similar comparison statements and combine them to generate the abstractive summary [52]. Similar sentences are represented by a tree.…”

Section: ) Methods Based On Treesmentioning

confidence: 99%

Section: ) Methods Based On Treesmentioning

confidence: 99%

A Comprehensive Review of Arabic Text Summarization

et al. 2022

View full text Add to dashboard Cite

show abstract

“…34 Although RNN techniques based on encoder-decoder structure achieve successful results, especially in short text summary, they have disadvantages such as producing repetitive words and not detecting rare and rarely mentioned words. 35 Hou et al 35 in their study, first transformed the news data set they obtained into plain text, then they used a sub-word model by applying word segmentation. In another phase of their work, they used pre-trained Gensim 36 toolkit to obtain word vectors.…”

Section: Related Workmentioning

confidence: 99%

Abstractive text summarization using deep learning with a new Turkish summarization benchmark dataset

Ertam

Aydın

2021

Concurrency and Computation

View full text Add to dashboard Cite

Exponential increase in the amount of textual data made available on the Internet results in new challenges in terms of accessing information accurately and quickly.Text summarization can be defined as reducing the dimensions of the expressions to be summarized without spoiling the meaning. Summarization can be performed as extractive and abstractive or using both together. In this study, we focus on abstractive summarization which can produce more human-like summarization results. For the study we created a Turkish news summarization benchmark dataset from various news agency web portals by crawling the news title, short news, news content, and keywords for the last 5 years. The dataset is made publicly available for researchers.The deep learning network training was carried out by using the news headlines and short news contents from the prepared dataset and then the network was expected to create the news headline as the short news summary. To evaluate the performance of this study, Rouge-1, Rouge-2, and Rouge-L were compared using precision, sensitivity and F1 measure scores. Performance values for the study were presented for each sentence as well as by averaging the results for 50 randomly selected sentences.The F1 Measure values are 0.4317, 0.2194, and 0.4334 for Rouge-1, Rouge-2, and Rouge-L respectively. Performance results show that the approach is promising for Turkish text summarization studies and the prepared dataset will add value to the literature.

show abstract

“…Abstractive approaches can generate better summaries using words other than those in the original document [46], with the advantage that they can reduce the length of the summary, compared to extractive approaches [47]. Several methods have been developed…”

Section: Related Work On Text Summarizationmentioning

confidence: 99%

WATS-SMS: A T5-Based French Wikipedia Abstractive Text Summarizer for SMS

et al. 2021

View full text Add to dashboard Cite

Text summarization remains a challenging task in the natural language processing field despite the plethora of applications in enterprises and daily life. One of the common use cases is the summarization of web pages which has the potential to provide an overview of web pages to devices with limited features. In fact, despite the increasing penetration rate of mobile devices in rural areas, the bulk of those devices offer limited features in addition to the fact that these areas are covered with limited connectivity such as the GSM network. Summarizing web pages into SMS becomes, therefore, an important task to provide information to limited devices. This work introduces WATS-SMS, a T5-based French Wikipedia Abstractive Text Summarizer for SMS. It is built through a transfer learning approach. The T5 English pre-trained model is used to generate a French text summarization model by retraining the model on 25,000 Wikipedia pages then compared with different approaches in the literature. The objective is twofold: (1) to check the assumption made in the literature that abstractive models provide better results compared to extractive ones; and (2) to evaluate the performance of our model compared to other existing abstractive models. A score based on ROUGE metrics gave us a value of 52% for articles with length up to 500 characters against 34.2% for transformer-ED and 12.7% for seq-2seq-attention; and a value of 77% for articles with larger size against 37% for transformers-DMCA. Moreover, an architecture including a software SMS-gateway has been developed to allow owners of mobile devices with limited features to send requests and to receive summaries through the GSM network.

show abstract

Abstractive Document Summarization via Neural Model with Joint Attention

Cited by 30 publications

References 10 publications

A Comprehensive Review of Arabic Text Summarization

A Comprehensive Review of Arabic Text Summarization

Abstractive text summarization using deep learning with a new Turkish summarization benchmark dataset

WATS-SMS: A T5-Based French Wikipedia Abstractive Text Summarizer for SMS

Contact Info

Product

Resources

About