Text Summarization Techniques: A Brief Survey

Allahyari, Mehdi; Pouriyeh, Seyedamin; Assefi, Mehdi; Safaei, Saeid; Trippe, Elizabeth D.; Gutiérrez, J.; Kochut, Krys J.

doi:10.48550/arxiv.1707.02268

Cited by 58 publications

(68 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automatic text summarization is the task of producing a concise and fluent summary while preserving key information content and overall meaning [2]. Extractive and Abstractive are the two main categories of summarization algorithms.…”

Section: Text Summarizationmentioning

confidence: 99%

“…Also for having an abstract, we implemented and used the abstractive text summarization method for the video [12]. Abstractive summarization methods interpret and examine the text by using advanced natural language techniques in order to generate a new shorter text that conveys the most important information from the original text [2].…”

Section: Document To Title Processmentioning

confidence: 99%

“…Image and video captioning with deep learning are used for the difficult task of recognizing the objects and actions in an image or video and creating a succinct meaningful sentence based on the contents found. Text summarization [2] is the task of generating a concise and fluent summary for a document(s) while preserving key information content. This paper proposes an architecture by utilizing the image/video captioning system and text summarization methods to make a title and an abstract for a long video.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Generation of Descriptive Titles for Video Clips Using Deep Learning

Amirian¹,

Rasheed²,

Taha³

et al. 2021

Preprint

View full text Add to dashboard Cite

Over the last decade, the use of Deep Learning in many applications produced results that are comparable to and in some cases surpassing human expert performance. The application domains include diagnosing diseases, finance, agriculture, search engines, robot vision, and many others. In this paper, we are proposing an architecture that utilizes image/video captioning methods and Natural Language Processing systems to generate a title and a concise abstract for a video. Such a system can potentially be utilized in many application domains, including, the cinema industry, video search engines, security surveillance, video databases/warehouses, data centers, and others. The proposed system functions and operates as followed: it reads a video; representative image frames are identified and selected; the image frames are captioned; NLP is applied to all generated captions together with text summarization; and finally, a title and an abstract are generated for the video. All functions are performed automatically. Preliminary results are provided in this paper using publicly available datasets. This paper is not concerned about the efficiency of the system at the execution time. We hope to be able to address execution efficiency issues in our subsequent publications.

show abstract

Section: Text Summarizationmentioning

confidence: 99%

Section: Document To Title Processmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Generation of Descriptive Titles for Video Clips Using Deep Learning

Amirian¹,

Rasheed²,

Taha³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The problem of generating summaries from customer feedback is modeled as a text summarization task (Nallapati et al, 2016;Allahyari et al, 2017; in the natural language processing (NLP) domain. Abstractive summarization models with transformer-based architecture have achieved success in a variety of summarization tasks Raffel et al, 2020;Zhang et al, 2020;Bao et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Improving Factual Consistency of Abstractive Summarization on Customer Feedback

Liu¹,

Sun²,

Gao

2021

Preprint

View full text Add to dashboard Cite

E-commerce stores collect customer feedback to let sellers learn about customer concerns and enhance customer order experience. Because customer feedback often contains redundant information, a concise summary of the feedback can be generated to help sellers better understand the issues causing customer dissatisfaction. Previous state-of-the-art abstractive text summarization models make two major types of factual errors when producing summaries from customer feedback, which are wrong entity detection (WED) and incorrect product-defect description (IPD). In this work, we introduce a set of methods to enhance the factual consistency of abstractive summarization on customer feedback. We augment the training data with artificially corrupted summaries, and use them as counterparts of the target summaries. We add a contrastive loss term into the training objective so that the model learns to avoid certain factual errors. Evaluation results show that a large portion of WED and IPD errors are alleviated for BART and T5. Furthermore, our approaches do not depend on the structure of the summarization model and thus are generalizable to any abstractive summarization systems.

show abstract

“…Huge GPT-2 [21] and following GPT-3 [3] models enjoyed great attention of the public with convincing stories from "new species of unicorns" to "colony of humans living in elevator shafts". 1 Even generation of realistic images from a written text prompt is now possible. 2 Lithuanian language can not enjoy the same attention and application of innovations as English.…”

Section: Introductionmentioning

confidence: 99%

Generating abstractive summaries of Lithuanian news articles using a transformer model

Stankevičius,

Lukoševičius

2021

Preprint

View full text Add to dashboard Cite

In this work, we train the first monolingual Lithuanian transformer model on a relatively large corpus of Lithuanian news articles and compare various output decoding algorithms for abstractive news summarization. Generated summaries are coherent and look impressive at the first glance. However, some of them contain misleading information that is not so easy to spot. We describe all the technical details and share our trained model and accompanying code in an online opensource repository, as well as some characteristic samples of the generated summaries.

show abstract

Text Summarization Techniques: A Brief Survey

Cited by 58 publications

References 34 publications

Automatic Generation of Descriptive Titles for Video Clips Using Deep Learning

Automatic Generation of Descriptive Titles for Video Clips Using Deep Learning

Improving Factual Consistency of Abstractive Summarization on Customer Feedback

Generating abstractive summaries of Lithuanian news articles using a transformer model

Contact Info

Product

Resources

About