Assessing shallow sentence scoring techniques and combinations for single and multi-document summarization

Oliveira, Hilário; Ferreira, Rafael; Lima, Rinaldo; Lins, Rafael Dueire; Freitas, Fred; Riss, Marcelo; Simske, Steven J.

doi:10.1016/j.eswa.2016.08.030

Cited by 50 publications

(48 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Para isso, as frases com maiores escores de relevância são selecionadas para compor o resumo. Para evitar redundância entre as sentenças selecionadas, utilizamos a heurística de que uma nova frase sóé inserida no resumo caso ela não possua similaridade do cosseno maior que 0,5 com cada uma das sentenças já incluídas no resumo [Oliveira et al 2016]. O processo de seleçãoé realizado de forma iterativa inserindo a frase com maior pontuação, desde que ela respeite o critério de similaridade anterior, até que o tamanho máximo do resumo seja alcançado.…”

Section: Ponderação Das Sentençasunclassified

“…Em geral, esses indicadores são baseados em técnicas estatísticas, como frequência, centralidade, ou em heurísticas, como posição das frases nos documentos. O trabalho desenvolvido por [Oliveira et al 2016] avaliou diversas técnicas de ponderação da relevância das frases nas tarefas de SAT de artigos de notícias escritos em inglês. Os autores avaliaram os métodos individualmente e combinados, além de utilizá-los como atributos adotando algoritmos de classificação.…”

Section: Introductionunclassified

See 1 more Smart Citation

Avaliando Algoritmos de Regressão para Sumarização Automática de Textos em Português do Brasil

Sodré¹,

Oliveira²

2019

Anais Do XVI Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2019)

View full text Add to dashboard Cite

A Sumarização Automática de Textos (SAT) é uma proeminente área de pesquisa, cujo objetivo é a criação automática de um resumo contendo as informações mais relevantes a partir de um ou mais documentos. Um dos principais desafios da SAT é identificar as informações mais relevantes que devem ser inseridas no resumo a ser gerado. Este trabalho tem por objetivo analisar a aplicação de algoritmos de regressão para estimar um escore de relevância das frases de uma coleção de artigos de notícias escritos em português do Brasil na tarefa de sumarização. Experimentos foram executados para avaliar diferentes métodos de estimação de relevância das frases, algoritmos de regressão, e comparar os resultados obtidos com outros trabalhos da literatura. Os resultados experimentais demonstraram que o algoritmo de regressão Bayesiana obteve os melhores resultados com base nas medidas de avaliação do ROUGE, atingindo uma taxa de 62,09% de cobertura.

show abstract

Section: Ponderação Das Sentençasunclassified

Section: Introductionunclassified

Avaliando Algoritmos de Regressão para Sumarização Automática de Textos em Português do Brasil

Sodré¹,

Oliveira²

2019

Anais Do XVI Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2019)

View full text Add to dashboard Cite

show abstract

“…This method relies on a predefined dictionary of sign expressions. This technique is calculated according to (4) -Sentences containing numerical data: Numerical information refers to the important information such as date, percentage, cost, feature, and so on [29], [31]. The score of the sentence Si is calculated using this feature according to (5):…”

Section: Sentences Containing Cue-phrasesmentioning

confidence: 99%

“…According to this assumption, the words that have a high frequency in the text are more important than other words. Of course, stop words are removed and all other words are stemmed before calculating the term frequency [31]. The importance of a sentence based term frequency is calculated according to (2):…”

Section: ) Scoring the Graph Nodesmentioning

confidence: 99%

Text Summarization of Multi-Aspect Comments in Social Networks in Persian Language

Shahverdian¹,

Saneifar²

2017

ijacsa

View full text Add to dashboard Cite

Abstract-Now-a-days, there are increasingly huge amount of user generated comments on the web. The user generated comments usually contains useful and essential information reflecting public's or customers' opinions. Since the information in the comments could be used for decision making, production or service improvement, and achieving user satisfaction, the systematic analysis of these comments is an essential need in so many domains including e-commerce, production, and social network analysis. However, the analysis of large volume of comments is a difficult and time-consuming task. Therefore, the need for a system which can convert this massive volume of comments to a useful and efficient summary is felt more and more. Text summarization leads to using more resources at higher speeds and getting richer information. According to numerous studies conducted in the field of multi-document summarization, few studies can be found that have been focused on the user generated comments in Persian language. In this paper, we propose a novel approach to summarize huge amount of comments in Persian, which is enough close to a human summarization. Our approach is based on semantic and lexical similarities and uses a graph-based summarization. We also propose a clustering to deal with multiple aspects (subjects) in a corpus of comments. According to the experiments, the summaries extracted by the proposed approach reached an average score of 8.75 out of 10, which improves the state-of-theart summarizer's score about 14 percent.

show abstract

“…Though, reflection based outlines requires phonetic investigation to develop new sentences from the first text [5,6]. Based on measurement, extraction based rundowns can be sorted into two ways i.e., non-specific or question subordinate [7].…”

Section: Introductionmentioning

confidence: 99%

An Abstract Study on Non-Identical Multi-Document Summarization Approaches

Rannels¹,

Falconieri²,

Phillips³

et al. 2018

IJRTER

View full text Add to dashboard Cite

Abstract-In the current situation the rate of development of data is growing exponentially in the World Wide Web. Thus, extricating legitimate and valuable data from enormous information has turned into a testing issue. As of late text summarization is perceived as one of the answer for remove applicable data from huge documents. Based on number of documents considered for summarization, the summarization assignment is ordered as single document or multi-document summarization. As opposed to single document, multi-document summarization is all the more trying for the analysts to discover exact synopsis from multiple documents. In this paper we have begun with presentation of multidocument summarization and after that have additionally examined examination and investigation of different methodologies which goes under the multidocument summarization. The paper additionally contains insights about the advantages and issues in the current techniques. This would particularly be useful for scientists working in this field of text information mining. By utilizing this information, scientists can fabricate new or blended based methodologies for multi-document summarization.

show abstract

Assessing shallow sentence scoring techniques and combinations for single and multi-document summarization

Cited by 50 publications

References 18 publications

Avaliando Algoritmos de Regressão para Sumarização Automática de Textos em Português do Brasil

Avaliando Algoritmos de Regressão para Sumarização Automática de Textos em Português do Brasil

Text Summarization of Multi-Aspect Comments in Social Networks in Persian Language

An Abstract Study on Non-Identical Multi-Document Summarization Approaches

Contact Info

Product

Resources

About