SummCoder: An unsupervised framework for extractive text summarization based on deep auto-encoders

Joshi, Akanksha; Fidalgo, Eduardo; Alegre, Enrique; Fernández-Robles, Laura

doi:10.1016/j.eswa.2019.03.045

Cited by 122 publications

(66 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An extractive approach based on event graph [41] used human crafted rules for generation of multidocument summary. Recently, the emergence of deep learning (DL) and reinforcement learning (RL) approaches [42][43][44][45] has gained attention of researchers, and their capabilities are exploited to enhance the text summarization task. However, the networks based on DL/RL need training on large amount of human crafted summaries, which are not easily available.…”

Section: Related Workmentioning

confidence: 99%

Sentence Embedding Based Semantic Clustering Approach for Discussion Thread Summarization

et al. 2020

View full text Add to dashboard Cite

Huge data on the web come from discussion forums, which contain millions of threads. Discussion threads are a valuable source of knowledge for Internet users, as they have information about numerous topics. The discussion thread related to single topic comprises a huge number of reply posts, which makes it hard for the forum users to scan all the replies and determine the most relevant replies in the thread. At the same time, it is also hard for the forum users to manually summarize the bulk of reply posts in order to get the gist of discussion thread. Thus, automatically extracting the most relevant replies from discussion thread and combining them to form a summary are a challenging task. With this motivation behind, this study has proposed a sentence embedding based clustering approach for discussion thread summarization. The proposed approach works in the following fashion: At first, word2vec model is employed to represent reply sentences in the discussion thread through sentence embeddings/sentence vectors. Next, K-medoid clustering algorithm is applied to group semantically similar reply sentences in order to reduce the overlapping reply sentences. Finally, different quality text features are utilized to rank the reply sentences in different clusters, and then the high-ranked reply sentences are picked out from all clusters to form the thread summary. Two standard forum datasets are used to assess the effectiveness of the suggested approach. Empirical results confirm that the proposed sentence based clustering approach performed superior in comparison to other summarization methods in the context of mean precision, recall, and F-measure.

show abstract

Section: Related Workmentioning

confidence: 99%

Sentence Embedding Based Semantic Clustering Approach for Discussion Thread Summarization

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Consider the topic 't' is incorrect to the other word in the document which is allocated as correct topic for each word in the web documents. 4. Find the probability of correctness across the topics 5.…”

Section: Topic Modelermentioning

confidence: 99%

“…These information are available in multiple webpages which are referring to a similar topic. This leads, the researchers and industrialist to consider the multi-document summarization to produce summary from multiple documents [4]. Summaries can likewise be sorted as either nonexclusive or question highlighted [5].…”

Section: Introductionmentioning

confidence: 99%

Multi-Documents Extractive Text Summarization using Node Centrality

Kuriakose,

Umadevi

2020

IJEAT

View full text Add to dashboard Cite

The advancement of technologies produce vast amount of data over the internet. The massive amount of information flooded in the webpages become more difficult to extract the meaningful insights. Social media websites are playing major role in publishing news events on the similar topic with different contents. Extracting the hidden information from the multiple webpages are tedious job for researchers and industrialists. This paper mainly focuses on gathering information from multiple webpages and to produce summary from those contents under similar topic. Multi-document extractive summarization has been developed using the graph based text summarization method. Proposed method builds a graph between the multi-documents using the Katz centrality of nodes. The performance of proposed GeSUM (Graph based Extractive Summarization) is evaluated with the ROUGE metrics.

show abstract

“…Different research efforts have been made to monitor Tor domains, and insights gained have been used to develop techniques that allow for the supervision of suspicious activities. These techniques range from solutions based on Natural Language Processing [ 15 , 16 ], to Computer Vision [ 17 , 18 ] or Graph Theory [ 19 , 20 ].…”

Section: Introductionmentioning

confidence: 99%

Rectification and Super-Resolution Enhancements for Forensic Text Recognition

Blanco‐Medina

Fidalgo

Alegre

et al. 2020

Sensors

View full text Add to dashboard Cite

Retrieving text embedded within images is a challenging task in real-world settings. Multiple problems such as low-resolution and the orientation of the text can hinder the extraction of information. These problems are common in environments such as Tor Darknet and Child Sexual Abuse images, where text extraction is crucial in the prevention of illegal activities. In this work, we evaluate eight text recognizers and, to increase the performance of text transcription, we combine these recognizers with rectification networks and super-resolution algorithms. We test our approach on four state-of-the-art and two custom datasets (TOICO-1K and Child Sexual Abuse (CSA)-text, based on text retrieved from Tor Darknet and Child Sexual Exploitation Material, respectively). We obtained a 0.3170 score of correctly recognized words in the TOICO-1K dataset when we combined Deep Convolutional Neural Networks (CNN) and rectification-based recognizers. For the CSA-text dataset, applying resolution enhancements achieved a final score of 0.6960. The highest performance increase was achieved on the ICDAR 2015 dataset, with an improvement of 4.83% when combining the MORAN recognizer and the Residual Dense resolution approach. We conclude that rectification outperforms super-resolution when applied separately, while their combination achieves the best average improvements in the chosen datasets.

show abstract

SummCoder: An unsupervised framework for extractive text summarization based on deep auto-encoders

Cited by 122 publications

References 21 publications

Sentence Embedding Based Semantic Clustering Approach for Discussion Thread Summarization

Sentence Embedding Based Semantic Clustering Approach for Discussion Thread Summarization

Multi-Documents Extractive Text Summarization using Node Centrality

Rectification and Super-Resolution Enhancements for Forensic Text Recognition

Contact Info

Product

Resources

About