A Survey of the State-of-the-Art Models in Neural Abstractive Text Summarization

Syed, Ayesha Ayub; Gaol, Ford Lumban; Matsuo, Tokuro

doi:10.1109/access.2021.3052783

Cited by 55 publications

(24 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Syed et al [17] presented a hidden layer multilayer perceptron to demonstrate character recognition. The character is identified by examining its forms and comparing its features.…”

Section: Literature Reviewmentioning

confidence: 99%

Support Vector Machine Based Handwritten Hindi Character Recognition and Summarization

Dhankhar¹,

Gupta²,

Memon³

et al. 2022

Computer Systems Science and Engineering

View full text Add to dashboard Cite

In today's digital era, the text may be in form of images. This research aims to deal with the problem by recognizing such text and utilizing the support vector machine (SVM). A lot of work has been done on the English language for handwritten character recognition but very less work on the under-resourced Hindi language. A method is developed for identifying Hindi language characters that use morphology, edge detection, histograms of oriented gradients (HOG), and SVM classes for summary creation. SVM rank employs the summary to extract essential phrases based on paragraph position, phrase position, numerical data, inverted comma, sentence length, and keywords features. The primary goal of the SVM optimization function is to reduce the number of features by eliminating unnecessary and redundant features. The second goal is to maintain or improve the classification system's performance. The experiment included news articles from various genres, such as Bollywood, politics, and sports. The proposed method's accuracy for Hindi character recognition is 96.97%, which is good compared with baseline approaches, and system-generated summaries are compared to human summaries. The evaluated results show a precision of 72% at a compression ratio of 50% and a precision of 60% at a compression ratio of 25%, in comparison to state-of-the-art methods, this is a decent result.

show abstract

“…Syed et al [17] presented a hidden layer multilayer perceptron to demonstrate character recognition. The character is identified by examining its forms and comparing its features.…”

Section: Literature Reviewmentioning

confidence: 99%

Support Vector Machine Based Handwritten Hindi Character Recognition and Summarization

Dhankhar¹,

Gupta²,

Memon³

et al. 2022

Computer Systems Science and Engineering

View full text Add to dashboard Cite

show abstract

“…For deep learning-based abstractive summarization, the sequence-to-sequence framework has become the main architecture (El-Kassas et al, 2021;Zhang et al, 2020). Lately, transformer-based architecture dramatically improves performance and has become a standard of neural abstractive models (Syed et al, 2021;Vaswani et al, 2017). Recent studies on neural abstractive models have focused on specific forms of datasets, such as long text (Cohan et al, 2018;Sharma et al, 2019), diverse domains (Hermann et al, 2015;Kornilova & Eidelman, 2019;Koupaee & Wang, 2018) and others.…”

Section: Text Summarizationmentioning

confidence: 99%

Structured abstract summarization of scientific articles: Summarization using full‐text section information

Nam

Zhu

2022

Asso for Info Science & Tech

View full text Add to dashboard Cite

The automatic summarization of scientific articles differs from other text genres because of the structured format and longer text length. Previous approaches have focused on tackling the lengthy nature of scientific articles, aiming to improve the computational efficiency of summarizing long text using a flat, unstructured abstract. However, the structured format of scientific articles and characteristics of each section have not been fully explored, despite their importance. The lack of a sufficient investigation and discussion of various characteristics for each section and their influence on summarization results has hindered the practical use of automatic summarization for scientific articles. To provide a balanced abstract proportionally emphasizing each section of a scientific article, the community introduced the structured abstract, an abstract with distinct, labeled sections. Using this information, in this study, we aim to understand tasks ranging from data preparation to model evaluation from diverse viewpoints. Specifically, we provide a preprocessed large‐scale dataset and propose a summarization method applying the introduction, methods, results, and discussion (IMRaD) format reflecting the characteristics of each section. We also discuss the objective benchmarks and perspectives of state‐of‐the‐art algorithms and present the challenges and research directions in this area.

show abstract

“…The success of the deep learning-based language models greatly improved the quality of abstractive summarization [27,[27][28][29]. Recently, Transformer-based models have become state-of-theart models for abstractive text summarization [30]. For example, BERTSum [29] leverages the strong language modeling capability of a pre-trained BERT [1] model to achieve high-quality abstractive summarization through transfer learning.…”

Section: Ts Systemmentioning

confidence: 99%

Attention-based Multi-hypothesis Fusion for Speech Summarization

Kano¹,

Ogawa²,

Delcroix³

et al. 2021

Preprint

View full text Add to dashboard Cite

Speech summarization, which generates a text summary from speech, can be achieved by combining automatic speech recognition (ASR) and text summarization (TS). With this cascade approach, we can exploit state-of-the-art models and large training datasets for both subtasks, i.e., Transformer for ASR and Bidirectional Encoder Representations from Transformers (BERT) for TS. However, ASR errors directly affect the quality of the output summary in the cascade approach. We propose a cascade speech summarization model that is robust to ASR errors and that exploits multiple hypotheses generated by ASR to attenuate the effect of ASR errors on the summary. We investigate several schemes to combine ASR hypotheses. First, we propose using the sum of sub-word embedding vectors weighted by their posterior values provided by an ASR system as an input to a BERT-based TS system. Then, we introduce a more general scheme that uses an attention-based fusion module added to a pre-trained BERT module to align and combine several ASR hypotheses. Finally, we perform speech summarization experiments on the How2 dataset and a newly assembled TED-based dataset that we will release with this paper 1 . These experiments show that retraining the BERT-based TS system with these schemes can improve summarization performance and that the attention-based fusion module is particularly effective.

show abstract

A Survey of the State-of-the-Art Models in Neural Abstractive Text Summarization

Cited by 55 publications

References 31 publications

Support Vector Machine Based Handwritten Hindi Character Recognition and Summarization

Support Vector Machine Based Handwritten Hindi Character Recognition and Summarization

Structured abstract summarization of scientific articles: Summarization using full‐text section information

Attention-based Multi-hypothesis Fusion for Speech Summarization

Contact Info

Product

Resources

About