Generating summary using sequence to sequence model

Zhao, Shuai; Deng, Encong; Liao, Mengfan; Liu, Wei; Mao, Weiming

doi:10.1109/itoec49072.2020.9141919

Cited by 6 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the extractive method weights and selects sentences from the input texts based on ranking criteria. The latter method is popular (i.e., especially in news domain [23]) and seems a more straightforward method, which tends to produce a higher efficiency summary than the abstractive-based summary [24]. Diving into the extractive method that we consider in this paper, there are various techniques used in addressing Arabic summarization, such as statistical/linguistic-based [8], [15], [9], [6], semantic/query-based [12], [7], [8], [21], [9], graph/optimization-based [10], [11], [25], [12], and machine learning [5], [13], [14], [20], [19], [15], [26], [27], [28].…”

Section: A Overview Of Ats Approachesmentioning

confidence: 99%

Leveraging DistilBERT for Summarizing Arabic Text: An Extractive Dual-Stage Approach

et al. 2021

View full text Add to dashboard Cite

Towards tackling the phenomenon of textual information overload that is exponentially pumping with redundancy over the Internet, this paper investigates a solution depending on the Automatic Text Summarization (ATS) method. The idea of ATS is to assist, e.g., online readers, in getting a simplified version of texts for preserving their time/effort required to skim a given large body of text. However, ATS is deemed as one of the most complex NLP applications, particularly for the Arabic language that has not been intelligently developed like the other Indo-European languages. Thus, we present an extractivebased summarizer (ArDBertSum) for text written in Arabic, relying on the DistilBERT model. Besides, we propose a domain-specific sentence-clauses segmentater (SCSAR) to support our ArDBertSum in further shortening long/complex sentences. The results of our experiments illustrate that our ArDBertSum yields the best performance, compared with non-heuristic Arabic summarizers, in producing an acceptable quality of candidate summaries. These experiments have been conducted on EASC-dataset (along with our proposed dataset) to report on (1) a statistical evaluation utilizing ROUGE metrics and (2) a specific human-based evaluation. The human evaluation results revealed promising perceptions; however, further works are needed to ameliorate the coherence and punctuation of the automatic summaries.

show abstract

Section: A Overview Of Ats Approachesmentioning

confidence: 99%

Leveraging DistilBERT for Summarizing Arabic Text: An Extractive Dual-Stage Approach

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In this section, we first present the basic theoretical framework of standard GAN in Part A, the characteristics of real seismic sequences are analyzed in Part B according to the evolution process of the seismic event. Finally, we also design the EQGAN model based on appropriate algorithms in Part C. Earthquake/Phase detection ConvNet incomplete/low SNR waveform Using transformation method [25] Eaethquake detection Unsupervised technique Microseismic dataset Using transformation method [26] Earthquake detection SCALODEEP Small training dataset Using generalizad deep learning based on a small daraset [27] Earthquake detection CPIC Small-sized dataset Using generalizad deep learning based on a small daraset [28] Earthquake detection CapsNet Small training dataset Using generalizad deep learning based on a small daraset [31] Synthesize speech HMM Speech dataset Developing a data augmentation approach [32] Text generation LSTM Text dataset Developing a data augmentation approach [33] Text summarization Seq2seq Text dataset Developing a data augmentation approach [29] Seismic data augmentation Conditional GAN Seismic dataset Developing a data augmentation approach [30] Short seismic waveform generation EarthuqakeGen Seismic dataset Developing a data augmentation approach A. THEORETICAL BASIS In 2014, Goodfellow [36] proposed the concept of GAN, an epoch-making unsupervised learning algorithm framework (Fig.…”

Section: Theory and Model Designmentioning

confidence: 99%

“…However, compared with the traditional recurrent neural network (RNN) algorithm, the training difficulty also increases because of too many parameters. Zhao et al [33] proposes the seq2seq based on LSTM together with an attention mechanism to improve the efficiency quality of text summarization, which, however, lack text information coherence. Although different DL models have been developed in these studies to achieve time series generation, they cannot fully represent the distribution of the original data.…”

Section: Introductionmentioning

confidence: 99%

Augmenting Seismic Data Using Generative Adversarial Network for Low-Cost MEMS Sensors

Wu¹,

Shin

Ahn

et al. 2021

IEEE Access

View full text Add to dashboard Cite

The performance of a deep learning (DL) model depends on sufficient training datasets and is related to the algorithm structure. Seismological research based on DL suffers from the lack of seismic data recorded by low-cost micro-electro-mechanical systems (MEMS) sensors whose data is usually polluted by different types of noise. Therefore, increasing seismic datasets is necessary for intelligently generating seismic data through data-augmentation techniques. However, it is difficult to characterize and measure the evolution process of seismic sequences, making the feature extraction and data generation of seismic sequences still a significant challenge. By combining the framework of Generative Adversarial Network (GAN) with long short-term memory (LSTM), attention mechanism and neural network (NN), a novel deep generation model (DGM) named EQGAN is developed to overcome the challenges, which can automatically capture the different time histories and dimension characteristics of seismic sequences, meanwhile stably generating high-quality seismic data. The reality of generated data is qualitatively clarified through the analysis of frequency domain and data autocorrelation distribution. Based on the High-throughput Screening (HTS) Theory, the quantitative evaluation index of statistical metrics is designed, and the generation performance of different machine learning models (standard GAN, LSTM, NN) is compared to prove the stability and effectiveness of EQGAN. The experimental results denote that the EQGAN has excellent stability and performance (up to 81%, much higher than that of other generation models), which provides a suitable data expansion approach for the field of seismological research.

show abstract