scholarly journals Reducing repetition in convolutional abstractive summarization

2021 ◽  
pp. 1-29
Author(s):  
Yizhu Liu ◽  
Xinyue Chen ◽  
Xusheng Luo ◽  
Kenny Q. Zhu
Keyword(s):  
Input Sequence ◽  
High Quality ◽  
Reading Experience ◽  
Source Document ◽  
Sentence Level ◽  
Proposed Model ◽  
Abstractive Summarization ◽  
Filter Mechanism

Abstract Convolutional sequence to sequence (CNN seq2seq) models have met success in abstractive summarization. However, their outputs often contain repetitive word sequences and logical inconsistencies, limiting the practicality of their application. In this paper, we find the reasons behind the repetition problem in CNN-based abstractive summarization through observing the attention map between the summaries with repetition and their corresponding source documents and mitigate the repetition problem. We propose to reduce the repetition in summaries by attention filter mechanism (ATTF) and sentence-level backtracking decoder (SBD), which dynamically redistributes attention over the input sequence as the output sentences are generated. The ATTF can record previously attended locations in the source document directly and prevent the decoder from attending to these locations. The SBD prevents the decoder from generating similar sentences more than once via backtracking at test. The proposed model outperforms the baselines in terms of ROUGE score, repeatedness, and readability. The results show that this approach generates high-quality summaries with minimal repetition and makes the reading experience better.

scholarly journals Context-Aware Neural Machine Translation for Korean Honorific Expressions

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1589
Author(s):  
Yongkeun Hwang ◽  
Yanghoon Kim ◽  
Kyomin Jung
Keyword(s):  
Machine Translation ◽  
Deep Neural Networks ◽  
Contextual Information ◽  
Context Aware ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Sentence Level ◽  
Proposed Model ◽  
The Given ◽  
The Relationship

Neural machine translation (NMT) is one of the text generation tasks which has achieved significant improvement with the rise of deep neural networks. However, language-specific problems such as handling the translation of honorifics received little attention. In this paper, we propose a context-aware NMT to promote translation improvements of Korean honorifics. By exploiting the information such as the relationship between speakers from the surrounding sentences, our proposed model effectively manages the use of honorific expressions. Specifically, we utilize a novel encoder architecture that can represent the contextual information of the given input sentences. Furthermore, a context-aware post-editing (CAPE) technique is adopted to refine a set of inconsistent sentence-level honorific translations. To demonstrate the efficacy of the proposed method, honorific-labeled test data is required. Thus, we also design a heuristic that labels Korean sentences to distinguish between honorific and non-honorific styles. Experimental results show that our proposed method outperforms sentence-level NMT baselines both in overall translation quality and honorific translations.

scholarly journals Modelling Perceived Risks Associated to the Entry of Complementors’ in Platform Enterprises: A Case Study

2018 ◽  
Vol 10 (9) ◽  
pp. 3272 ◽  
Author(s):  
Elena-Teodora Miron ◽  
Anca Purcarea ◽  
Olivia Negoita
Keyword(s):  
Literature Review ◽  
Perceived Risk ◽  
Asset Specificity ◽  
Third Party ◽  
High Quality ◽  
Perceived Risks ◽  
Proposed Model ◽  
Perceived Environmental Uncertainty ◽  
Main Attraction

Third-party innovators, i.e., complementors, in platform enterprises develop and commercialize add-on products which are one of the main attraction points for customers. To ensure a sustainable evolution of the enterprise, the platform owner needs to attract and retain high-quality third-party innovators. We posit that the transaction costs incurred upon joining the enterprise as well as the controls imposed by the platform owner throughout the development and commercialization process shape the innovator’s perceived risk and influence his decision on whether to join or not. Based on a literature review, the paper at hand proposes a conceptual model for complementors to assess their perceived risk and subsequently evaluates the model in a case study of a platform enterprise for IT-based modelling tools. While some of the propositions are validated, i.e., that informational controls decrease the perceived environmental uncertainty and implicitly the perceived risks, other propositions, such as the fact that asset specificity is a deterrent to entering the platform enterprise could not be validated. Further case studies are necessary to provide a conclusive proof of the proposed model.

Rough Set Theory Application in Online Course Satisfaction

2011 ◽  
Vol 271-273 ◽  
pp. 1239-1242
Author(s):  
Shao Jun Chen
Keyword(s):  
Set Theory ◽  
Rough Set ◽  
Rough Set Theory ◽  
Online Courses ◽  
Educational Environment ◽  
Course Satisfaction ◽  
Online Course ◽  
High Quality ◽  
Proposed Model ◽  
Theory Application

The most important issue for online courses is to provide learners with high quality satisfacion. In order to resolve the question and evaluating course satisfaction , rough set theory is proposed in this article, by which we reduce 10 attributes to 5 and get the index of value assessment.As a result, teachers can make an adjustment to achieve better effect in teaching by taking advantage of the method.The proposed model can be applied to not only a network environment but also remote educational environment.

scholarly journals A model for the development of high quality training of tourism professionals through the use of computer 3D-tours

2021 ◽  
Vol 30 (1) ◽  
pp. 90-99
Author(s):  
Mykhailo I. Lepkyi ◽  
Liudmyla Y. Matviichuk ◽  
Tetiana V. Lysiuk ◽  
Oksana S. Tereshchuk ◽  
Volodymyr M. Podolak
Keyword(s):  
Information And Communication Technologies ◽  
Professional Training ◽  
Communication Technologies ◽  
Educational Process ◽  
High Quality ◽  
Professional Skills ◽  
Proposed Model ◽  
Information And Communication ◽  
Tourism Professionals ◽  
Ict Tools

The article is focused on the problem of training future tourism specialists using informational and communication technologies. The educational process of preparation requires changing the educational and methodological support in order to give the students the opportunities to master modern professional tools, technologies, methods of creating high quality tourist products. To solve this problem, the authors propose a model for the development of high quality training of tourism professionals through the use of computer 3D-tours. The development of this model took into account the theoretical and methodological basis regarding the professional training of future specialists in the field of tourism, the results of the analysis of educational programs, curricula for training students of the speciality “Tourism” and the data of the pilot experiment. It consists of the following main blocks. The conceptual-oriented block includes concepts, approaches, principles of participation, information and communication technologies. The content-technological block includes the content of the educational project of developing 3D-tours, levels of professional knowledge and skills, as well as types of familiriazation with ICT tools. The educational content of the model takes into account the practical mastery of the student’s professional skills in the development of various 3D-tours. During this process, the ICT tools are introduced gradually in a certain order. The organization-activity block of the model includes forms of organizing the study and technologies for studying. This model entails the involvement of classroom-based and remote, individual, and group forms of organization of the educational process, organization of project development for a detailed analysis of educational topics. The assessment-resultative block includes criteria, metrics and levels. During the development of the model, the results of the activity of thesubjects of the educational process were analyzed in accordance with two groups of criteria: the criterion of formation of professional theoretical knowledge, practical skills of 3D-tour development and the criterion of the level of using modern software and technical means in creative educational development. The developed model allows for increasing the quality of training of future tourism specialists. During the practical application of the proposed model, virtual 3D-tours were developed. Their development has shown the possibility of implementing the model of development of training of specialists in tourism by using computer 3D-tours with the use of modern ICT tools in the study of special disciplines and the attaining professional skills.

scholarly journals Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation

2020 ◽  
Vol 34 (05) ◽  
pp. 7797-7804
Author(s):  
Goran Glavašš ◽  
Swapna Somasundaran
Keyword(s):  
State Of The Art ◽  
Language Transfer ◽  
Text Segmentation ◽  
Word Embeddings ◽  
Neural Architecture ◽  
Text Coherence ◽  
Sentence Level ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Cross Lingual

Breaking down the structure of long texts into semantically coherent segments makes the texts more readable and supports downstream applications like summarization and retrieval. Starting from an apparent link between text coherence and segmentation, we introduce a novel supervised model for text segmentation with simple but explicit coherence modeling. Our model – a neural architecture consisting of two hierarchically connected Transformer networks – is a multi-task learning model that couples the sentence-level segmentation objective with the coherence objective that differentiates correct sequences of sentences from corrupt ones. The proposed model, dubbed Coherence-Aware Text Segmentation (CATS), yields state-of-the-art segmentation performance on a collection of benchmark datasets. Furthermore, by coupling CATS with cross-lingual word embeddings, we demonstrate its effectiveness in zero-shot language transfer: it can successfully segment texts in languages unseen in training.

scholarly journals Modeling Dynamic Trust and Risk Evaluation Based on High-Order Moments

2015 ◽  
Vol 2015 ◽  
pp. 1-9 ◽  
Author(s):  
Yan Gao ◽  
Zhiyong Dai ◽  
Wenfen Liu
Keyword(s):  
Risk Evaluation ◽  
Hypothesis Test ◽  
Evaluation Model ◽  
High Order ◽  
Direct Trust ◽  
Proposed Model ◽  
Dynamic Trust ◽  
The Stability ◽  
Coefficient Of Skewness ◽  
Filter Mechanism

This paper proposes a dynamic trust and risk evaluation model based on high-order moments. The credibility of an entity is measured with trust degree and risk value comprehensively. Firstly, considering the dynamic and time decay characters of trust, a time attenuation function is defined, and direct trust is further expressed. Subsequently, in order to improve the accuracy of feedback trust, a filter mechanism is constructed to eliminate the false feedback, combining coefficient of skewness with hypothesis test. More importantly, the weights of direct trust and feedback trust are derived subjectively and adaptively with the moments and frequency of direct interactions. Furthermore, risk is evaluated with direct risk and feedback risk, which are obtained by mainly using coefficient of variation and coefficient of kurtosis. Risk value can be used to measure the stability of providing services. Simulation results show that the proposed model not only has high accuracy, but also resists effectively collusive attacks and strategic malicious behaviors.

Theme in discourse

2004 ◽  
Vol 11 (2) ◽  
pp. 213-249 ◽  
Author(s):  
Peter Crompton
Keyword(s):  
Theoretical Basis ◽  
Initial Position ◽  
Conclusive Evidence ◽  
High Quality ◽  
Argumentative Text ◽  
Thematic Progression ◽  
Sentence Level ◽  
Universal Feature ◽  
Argumentative Texts ◽  
Point Of Departure

Fries (1981) hypothesises that the textual phenomena of ‘thematic progression’ (TP) (Danesˇ 1974) and ‘method of development’ (MOD) provide discourse evidence for the function proposed by Halliday (1967) for Theme, in particular that ‘initial position in the sentence, or sentence-level Theme, means “point of departure of the sentence as message”‘. This paper discusses the theoretical basis for this hypothesis, in particular the relation between TP and MOD, and reviews previous empirical research. Further research conducted by the author is described, into global proportions of TP, TP patterning, and the relation between TP and rhematic progression (RP) in a small corpus of 80 short argumentative texts. It was found that only small proportions of either argumentative text, or high-quality argumentative text could be considered as having a MOD. It was also found that texts had comparable levels of TP and RP. It is concluded that MOD is not a universal feature of discourse organisation, and therefore not conclusive evidence for Fries’s original hypothesis.

scholarly journals Abstractive Text Summary of COVID-19 Documents based on LSTM Method and Word Embedding

Webology ◽  
2021 ◽  
Vol 18 (2) ◽  
pp. 1011-1022
Author(s):  
Saja Naeem Turky ◽  
Ahmed Sabah Ahmed AL-Jumaili ◽  
Rajaa K. Hasoun
Keyword(s):  
Deep Learning ◽  
Domain Knowledge ◽  
Input Sequence ◽  
Word Embedding ◽  
Suggested Model ◽  
Specific Domain ◽  
Scientific Texts ◽  
Proposed Model ◽  
Pass Through ◽  
Single Statement

An abstractive summary is a process of producing a brief and coherent summary that contains the original text's main concepts. In scientific texts, summarization has generally been restricted to extractive techniques. Abstractive methods that use deep learning have proven very effective in summarizing articles in public fields, like news documents. Because of the difficulty of the neural frameworks for learning specific domain- knowledge especially in NLP task, they haven't been more applied to documents that are related to a particular domain such as the medical domain. In this study, an abstractive summary is proposed. The proposed system is applied to the COVID-19 dataset which a collection of science documents linked to the coronavirus and associated illnesses, in this work 12000 samples from this dataset have been used. The suggested model is an abstractive summary model that can read abstracts of Covid-19 papers then create summaries in the style of a single-statement headline. A text summary model has been designed based on the LSTM method architecture. The proposed model includes using a glove model for word embedding which is converts input sequence to vector forms, then these vectors pass through LSTM layers to produce the summary. The results indicate that using an LSTM and glove model for word embedding together improves the summarization system's performance. This system was evaluated by rouge metrics and it achieved (43.6, 36.7, 43.6) for Rouge-1, Rouge-2, and Rouge-L respectively.

scholarly journals A Region-Based Efficient Network for Accurate Object Detection

2021 ◽  
Vol 38 (2) ◽  
pp. 481-494
Author(s):  
Yurong Guan ◽  
Muhammad Aamir ◽  
Zhihua Hu ◽  
Waheed Ahmed Abro ◽  
Ziaur Rahman ◽  
...  
Keyword(s):  
Object Detection ◽  
Detection Efficiency ◽  
Visual Object ◽  
Average Precision ◽  
High Quality ◽  
Image Objects ◽  
Object Proposal ◽  
Proposed Model ◽  
Image Object Detection ◽  
Image Object

Object detection in images is an important task in image processing and computer vision. Many approaches are available for object detection. For example, there are numerous algorithms for object positioning and classification in images. However, the current methods perform poorly and lack experimental verification. Thus, it is a fascinating and challenging issue to position and classify image objects. Drawing on the recent advances in image object detection, this paper develops a region-baed efficient network for accurate object detection in images. To improve the overall detection performance, image object detection was treated as a twofold problem, involving object proposal generation and object classification. First, a framework was designed to generate high-quality, class-independent, accurate proposals. Then, these proposals, together with their input images, were imported to our network to learn convolutional features. To boost detection efficiency, the number of proposals was reduced by a network refinement module, leaving only a few eligible candidate proposals. After that, the refined candidate proposals were loaded into the detection module to classify the objects. The proposed model was tested on the test set of the famous PASCAL Visual Object Classes Challenge 2007 (VOC2007). The results clearly demonstrate that our model achieved robust overall detection efficiency over existing approaches using fewer or more proposals, in terms of recall, mean average best overlap (MABO), and mean average precision (mAP).

scholarly journals Text Summarization using Extractive and Abstractive Methods

2021 ◽  
Vol 40 ◽  
pp. 03023
Author(s):  
Saurabh Varade ◽  
Ejaaz Sayyed ◽  
Vaibhavi Nagtode ◽  
Shilpa Shinde
Keyword(s):  
Input Sequence ◽  
Link Analysis ◽  
Attention Mechanism ◽  
Text Summarization ◽  
Ranking Algorithm ◽  
Text File ◽  
Extractive Summarization ◽  
Ranking Algorithms ◽  
Original Meaning ◽  
Abstractive Summarization

Text Summarization is a process where a huge text file is converted into summarized version which will preserve the original meaning and context. The main aim of any text summarization is to provide a accurate and precise summary. One approach is to use a sentence ranking algorithm. This comes under extractive summarization. Here, a graph based ranking algorithm is used to rank the sentences in the text and then top k-scored sentences are included in the summary. The most widely used algorithm to decide the importance of any vertex in a graph based on the information retrieved from the graph is Graph Based Ranking Algorithm. TextRank is one of the most efficient ranking algorithms which is used for Web link analysis that is for measuring the importance of website pages. Another approach is abstractive summarization where a LSTM encoder decoder model is used along with attention mechanism which focuses on some important words from the input. Encoder encodes the input sequence and decoder along with attention mechanism gives the summary as the output.

Sign in / Sign up

Export Citation Format

Share Document