Word-sentence co-ranking for automatic extractive text summarization

Fang, Changjian; Mu, Dejun; Deng, Zhenghong; Wu, Zhang

doi:10.1016/j.eswa.2016.12.021

Cited by 102 publications

(48 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This approach provides a synchronization of the final summary generated and the original text by extracting top k-sentences from individual cluster containing sentences thereby sorting the above sentences with their appearance in the initial text. [8] This research article proposed a technique for text summarization with the help of a model called as CoRank model. CoRank model is a word sentence-based model.…”

Section: IImentioning

confidence: 99%

An Extractive Summarization Technique for Text Documents

Dantis*,

Fernandes,

Rodrigues

2019

IJEAT

View full text Add to dashboard Cite

In order to read as well as search information quickly, there was a need to reduce the size of the documents without any changes to its content. Therefore, in order to solve this problem, there was a solution to it by introducing a technique called as automatic text summarization which is used to generate summaries from the input document by condensing large sized input documents into smaller documents without losing its meaning as well as relevancy with respect to the original document. Text summarization stands for shortening of text into accurate, meaningful sentences. The paper shows an implementation of summarization of the original document by scoring the sentence based on term frequency and inverse document frequency matrix. The entire record was compressed so that only the relevant sentences in the document were retained. This technique can be applicable in various applications like automating text documents, quicker understanding of documents because of summarization

show abstract

Section: IImentioning

confidence: 99%

An Extractive Summarization Technique for Text Documents

Dantis*,

Fernandes,

Rodrigues

2019

IJEAT

View full text Add to dashboard Cite

show abstract

“…Some graph-based document clustering or ranking algorithms are also used to incorporate semantic role of information in text summary (Ferreira et al, 2014a;Yan and Wan, 2014;Sankar and Sobha, 2009). With the assumption that mutual influence between sentences and words can boost the sentence score, Fang et al (2017) proposed unsupervised graph-based word-sentence co-ranking model to convey the intrinsic status of words and sentences more accurately.…”

Section: Related Workmentioning

confidence: 99%

“…It is gradually used in many sectors like data mining of textual databases, web-based information retrieval, generating abstract of technical papers, generating highlights of news domain and many more (Babar and Patil, 2015). Text summary is generated by following some sequential steps which includes preprocessing and sentence scoring to determine which sentences are essential and vital to the document (Ferreira et al, 2013;Fang et al, 2017). The main objective of text summarisation is to quickly find relevant information contents and generate a condensed replica of original document (Meena and Gopalani, 2014).…”

Section: Introductionmentioning

confidence: 99%

Fuzzy logic-based single document summarisation with improved sentence scoring technique

Patel

Chhinkaniwala

2018

IJKEDM

View full text Add to dashboard Cite

Text summarisation is compressed or condensed version of any text document. Due to increasing use of digitisation, massive amount of information is available on internet. Text summarisation is an emerging alternative for users to find relative information in automated shortened versions. In this paper we propose single document summarisation technique using shallow features of sentence to generate summary. The weight of sentences is calculated by applying score of different words and sentence-based statistical features. Here, most salient sentences are selected based on weight of sentences and are put together to generate summary. This is modeled using fuzzy inference system. This approach utilises fuzzy inference and fuzzy measures to find most significant sentences. The result of our proposed method is compared with other methods using recall oriented understudy for Gisting evaluation (ROUGE-N) measures on document understanding conferences (DUC) 2002 dataset and results show that our proposed method outperforms a few baseline methods.

show abstract

“…Perhaps, the most popular traditional text representation is the bag‐of‐words (BOW) or bag of n‐grams, in which words are represented by one‐hot encoding. Several summarization methods are using BOW for sentence scoring and selecting . Despite their simplicity, they have many drawbacks, such as poor sense with semantics, sparseness, and high‐dimensionality, which make it unable to produce a good representation .…”

Section: Introductionmentioning

confidence: 99%

EcForest: Extractive document summarization through enhanced sentence embedding and cascade forest

Yang

Al-Sabahi

et al. 2019

Concurrency and Computation

View full text Add to dashboard Cite

We present EcForest, an extractive summarization model through Enhanced Sentence Embedding and Cascade Forest. Sentence representation is of great significance for many summarization methods. Bag-of-words mostly fails to grasp the semantics, and typical embedding models cannot capture more complex semantic features, such as polysemy and the meaning of a phrase, which is usually ignored by simply averaging the word embeddings included in a sentence. To this end, we propose Enhanced Sentence Embedding (ESE) model to solve such drawbacks via mapping several valid features to dense vectors. Essentially, the enhanced sentence embedding is a novel model for improving the distributed representation of sentence. Our sentence embedding model is universally applicable and it can be adapted to other NLP tasks. Moreover, deep forest is used as a sentence extraction algorithm for its robustness to the hyper-parameters and its efficient training algorithm compared to deep neural network.The evaluation of variant models proposed in this work proves the validation of the enhanced sentence embedding. The comparison results between EcForest and several baselines on two different datasets demonstrate that the proposed summarization model performs better than or with high competitiveness to the state-of-the-art.

show abstract

Word-sentence co-ranking for automatic extractive text summarization

Cited by 102 publications

References 11 publications

An Extractive Summarization Technique for Text Documents

An Extractive Summarization Technique for Text Documents

Fuzzy logic-based single document summarisation with improved sentence scoring technique

EcForest: Extractive document summarization through enhanced sentence embedding and cascade forest

Contact Info

Product

Resources

About