Filters








4,501 Hits in 10.6 sec

An Automatic Abstractive Text Summarization System

Nasid Habib Barna, Hasnain Heickal
2022 Dhaka University Journal of Applied Science and Engineering  
In this work we propose a novel architecture incorporating advanced word embedding layer and topical feature with a pointer generator network to generate more topic oriented summaries in a logically sequenced  ...  Abstractive text summarization is one of the most interesting problems in the research field of Natural Language Processing.  ...  The research on extractive text summarization began with the method of extracting important sentences using features like word and phrase frequency [1] .  ... 
doi:10.3329/dujase.v6i2.59217 fatcat:6lzpe27rgvbufgyvmtn2ylom2e

An Abstractive Summarizer Based on Improved Pointer-Generator Network

Wenbo Nie, Wei Zhang, Xinle Li, Yao Yu
2019 2019 34rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)  
Second, the ability to extract words from the original text is improved by using the multi-hop attention mechanism, which improves the ability of the model to process out-of-vocabulary words.  ...  Aiming at the problems of insufficient semantic understanding, fluency and accuracy of abstracts in the field of neural abstractive summarization, an automatic text summarization model is proposed.  ...  We follow the process of constantly observing the original text and the generated summary when people do information extraction, and improve the copy probability based on the baseline pointer-generator  ... 
doi:10.1109/yac.2019.8787620 fatcat:eg4cddnldze6fcoxpsiabig35u

Improved Document Modelling with a Neural Discourse Parser [article]

Fajri Koto, Jey Han Lau, Timothy Baldwin
2019 arXiv   pre-print
We find that the proposed approach leads to improvements in all cases.  ...  We empirically investigate the benefit of the proposed approach on two different tasks: abstractive summarization and popularity prediction of online petitions.  ...  Our experiment has two pointer-generator network baselines: (1) one without the coverage mechanism ("PG"); and (2) one with the coverage mechanism ("PG+Cov"; Section 4.1).  ... 
arXiv:1911.06919v1 fatcat:zhd6e2rk4bf7tialzow5kcu754

Aspect-Aware Multimodal Summarization for Chinese E-Commerce Products

Haoran Li, Peng Yuan, Song Xu, Youzheng Wu, Xiaodong He, Bowen Zhou
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We present an abstractive summarization system that produces summary for Chinese e-commerce products. This task is more challenging than general text summarization.  ...  Thus, the summarizer needs to capture the most attractive aspects of a product that resonate with potential purchasers.  ...  Pointer-Generator (PG) is a text-based seq2seq network model with an attention and copying mechanism.  ... 
doi:10.1609/aaai.v34i05.6332 fatcat:5pc2frcxzfbstgyqlvrpmb7qvi

Selective Attention Encoders by Syntactic Graph Convolutional Networks for Document Summarization [article]

Haiyang Xu, Yun Wang, Kun Han, Baochang Ma, Junwen Chen, Xiangang Li
2020 arXiv   pre-print
We evaluate our approach on the CNN/Daily Mail text summarization dataset.  ...  Abstractive text summarization is a challenging task, and one need to design a mechanism to effectively extract salient information from the source text and then generate a summary.  ...  Abstractive: [19] firstly apply neural networks for text summarization by using a local attention-based model to generate word conditioned on the input sentence.  ... 
arXiv:2003.08004v1 fatcat:bgo3feq4kjambokv442oziyy3u

Bottom-Up Abstractive Summarization

Sebastian Gehrmann, Yuntian Deng, Alexander Rush
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
We use this selector as a bottom-up attention step to constrain the model to likely phrases. We show that this approach improves the ability to compress text, while still generating fluent summaries.  ...  Neural network-based methods for abstractive summarization produce outputs that are more fluent than other techniques, but which can be poor at content selection.  ...  Grosz for helpful discussions and feedback on early stages of this work. We further thank the three anonymous reviewers. This work was supported by a Samsung Research Award.  ... 
doi:10.18653/v1/d18-1443 dblp:conf/emnlp/GehrmannDR18 fatcat:e4sptpdsozconn4u3li3ghcswq

Abstractive Summarization of Document using Dual Encoding Framework

Monika H. Rajput, B. R. Mandre
2020 International Journal of Computer Applications  
To deal with this problem, an abstractive summarization of documents using an encoder decoder based approach is proposed.  ...  Text summarization solves this problem, it minifies text such that repeated data are removed and important information is extracted and represented in the concise way which can help us to understand the  ...  ABS and an additional log linear extractive summarization model with hand crafted features [1] . 3) RAS-Elman -In this, summarization is performed using an attentive encoder and RNN based decoder [2  ... 
doi:10.5120/ijca2020920544 fatcat:nes4ox7mendhvjg7woq4nuqwku

Point-less: More Abstractive Summarization with Pointer-Generator Networks [article]

Freek Boutkan, Jorn Ranzijn, David Rau, Eelco van der Wel
2019 arXiv   pre-print
The Pointer-Generator architecture has shown to be a big improvement for abstractive summarization seq2seq models.  ...  However, the summaries produced by this model are largely extractive as over 30% of the generated sentences are copied from the source text.  ...  In extractive summarization, fragments of the source text are concatenated to generate a summary [1] .  ... 
arXiv:1905.01975v1 fatcat:mspjinzpmfezvc64tdnws7an3u

Learning Syntactic and Dynamic Selective Encoding for Document Summarization [article]

Haiyang Xu, Yahao He, Kun Han, Junwen Chen, Xiangang Li
2020 arXiv   pre-print
Text summarization aims to generate a headline or a short summary consisting of the major information of the source text.  ...  The proposed model has been evaluated on CNN/Daily Mail summarization datasets and the experimental results show that the proposed approach outperforms baseline approaches.  ...  summarization. • Graph-Based Model [9] proposes a novel abstractive graph-based attention mechanism in the Seq2Seq frame-• Pointer-generator+Coverage(Po-Gen+Cov) [8] improves the standard Seq2Seq  ... 
arXiv:2003.11173v1 fatcat:ixwfaqy6tvgohcnlb5owkfx2ai

Bottom-Up Abstractive Summarization [article]

Sebastian Gehrmann, Yuntian Deng, Alexander M. Rush
2018 arXiv   pre-print
We use this selector as a bottom-up attention step to constrain the model to likely phrases. We show that this approach improves the ability to compress text, while still generating fluent summaries.  ...  Neural network-based methods for abstractive summarization produce outputs that are more fluent than other techniques, but which can be poor at content selection.  ...  Grosz for helpful discussions and feedback on early stages of this work. We further thank the three anonymous reviewers. This work was supported by a Samsung Research Award.  ... 
arXiv:1808.10792v2 fatcat:sha4wa2uwjflfd5uw3dxegnkv4

Improving Abstractive Text Summarization with History Aggregation [article]

Pengcheng Liao, Chuang Zhang, Xiaojun Chen, Xiaofei Zhou
2019 arXiv   pre-print
A high-quality summarization system usually depends on strong encoder which can refine important information from long input texts so that the decoder can generate salient summaries from the encoder's  ...  In this paper, we propose an aggregation mechanism based on the Transformer model to address the challenge of long text representation.  ...  Extractive summarization is easier, but abstractive summarization is more like the way humans process text. This paper focuses on the abstractive approach.  ... 
arXiv:1912.11046v1 fatcat:ca2m3ll55nbjlevjwwrbmxvc44

Abstractive Summarization Improved by WordNet-Based Extractive Sentences [chapter]

Niantao Xie, Sujian Li, Huiling Ren, Qibin Zhai
2018 Lecture Notes in Computer Science  
In this paper, in order to improve the semantic relevance of abstractive summaries, we adopt the WordNet based sentence ranking algorithm to extract the sentences which are most semantically to one text  ...  Still, how to improve abstractive methods with extractive methods is a good research direction, since extractive methods have their potentials of exploiting various efficient features for extracting important  ...  Acknowledgments We thank the anonymous reviewers for their insightful comments on this paper.  ... 
doi:10.1007/978-3-319-99495-6_34 fatcat:5j3bn2doqrhxfaatvswh7h66bq

StructSum: Summarization via Structured Representations [article]

Vidhisha Balachandran, Artidoro Pagnoni, Jay Yoon Lee, Dheeraj Rajagopal, Jaime Carbonell, Yulia Tsvetkov
2021 arXiv   pre-print
We show that our summarization framework, trained on the CNN/DM dataset, improves the coverage of content in the source documents, generates more abstractive summaries by generating more novel n-grams,  ...  Our framework complements standard encoder-decoder summarization models by augmenting them with rich structure-aware document representations based on implicitly learned (latent) structures and externally-derived  ...  StructSum uses the pointer-generator network as the base model.  ... 
arXiv:2003.00576v2 fatcat:mj5rc4wlozfqzjat4dzrn67iru

MeetSum: Transforming Meeting Transcript Summarization using Transformers! [article]

Nima Sadri, Bohan Zhang, Bihan Liu
2021 arXiv   pre-print
Moreover, a coverage mechanism is used to avoid repetition of words in the generated summary.  ...  In this paper, we utilize a Transformer-based Pointer Generator Network to generate abstract summaries for meeting transcripts.  ...  Summarization can happen using either an extractive or abstractive approach.  ... 
arXiv:2108.06310v1 fatcat:kcpn6w4eivhddkfucgd7ckgq6q

A Study on Seq2seq for Sentence Compressionin Vietnamese

Thi-Trang Nguyen, Huu-Hoang Nguyen, Kiem-Hieu Nguyen
2020 Pacific Asia Conference on Language, Information and Computation  
Text summarization is an important yet challenging task in natural language processing. In this paper, we investigate Pointer Generator Networks for sentence compression.  ...  Using Vietnamese as a case study, our model could yield sentence summaries with high quality of syntax, factual correctness and completeness.  ...  Extractive approaches attempts to identify salient parts of the source text and assembles them into a summary.  ... 
dblp:conf/paclic/NguyenNN20 fatcat:jwawsode6jhvfhd635sq5w7vnq
« Previous Showing results 1 — 15 out of 4,501 results