Document Summarization via Self-Present Sentence Relevance Model

Li, Xiaodong; Zhu, Shanfeng; Xie, Haoran; Li, Qing

doi:10.1007/978-3-642-37450-0_24

Cited by 6 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To validate the effectiveness of SSSR, We compare our experimental results with other representative summarization algorithms, including a ranking model: Self-Present Sentence Relevance Model (SPSR) [24], two selection models: DSDR and TopicDSDR [25], and two baselines offered by NIST.…”

Section: A Dataset and Evaluation Metricmentioning

confidence: 99%

Text Summarization Based on Sentence Selection with Semantic Representation

Zhang

Wang

et al. 2014

2014 IEEE 26th International Conference on Tools With Artificial Intelligence

View full text Add to dashboard Cite

Text summarization is of great importance to solve information overload. Salience and coverage are two most important issues for summaries. Most existing models extract summaries by selecting the top sentences with highest scores without using the relationships between sentences, and usually represent the sentences simply basing on lexical or statistical features. As a result, those models can not achieve salience or coverage very well. In this paper, we propose a novel summarization model called Sentence Selection with Semantic Representation (SSSR). SSSR ensures both salience and coverage by learning semantic representations for sentences and applying a well-designed selection strategy to select summary sentences. The selection strategy used in SSSR is to select sentences that can reconstruct the original document with least distortion by means of linear combination. Besides, we improve our selection strategy by reducing redundant information. Then we learn two semantic representations for sentences: (1) weighted mean of word embeddings; (2) deep coding. Both of them are semantic and compact, and can capture similarities between sentences. Extensive experiments on datasets DUC2006 and DUC2007 validate our model.

show abstract

Section: A Dataset and Evaluation Metricmentioning

confidence: 99%

Text Summarization Based on Sentence Selection with Semantic Representation

Zhang

Wang

et al. 2014

2014 IEEE 26th International Conference on Tools With Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…The Self-Present Sentence Relevance (SPSR) summarization model is to construct the latent relevance structure among sentences as link information, and believe a link between two sentences has a mutual emphasis effect. The potential key sentences will be emphasized more in the model and thus gain higher scores for further summarization [11]. SPSR is defined as a sextet, which is T, V, F, E, W, S :…”

Section: Summarization Modelmentioning

confidence: 99%

“…of Algorithm 1 is proved in [11]. Iteration number N is determined specifically to different corpus.…”

Section: Summarization Modelmentioning

confidence: 99%

Does Summarization Help Stock Prediction? A News Impact Analysis

Xie

Song

et al. 2015

IEEE Intell. Syst.

Self Cite

View full text Add to dashboard Cite

In this paper, we study the problem of how news summarization can help stock price prediction. We propose a generic stock price prediction framework to enable the use of different external signals to predict the stock prices. We suggest the use of a summarization model to generate signals from news articles, which are then evaluated by whether they can improve the prediction of stock's daily return. Experiments are conducted on five-year Hong Kong Stock Exchange data, with the news reported by FINET. Evaluations are done at individual stock level, sector index level and market index level. Results show that the prediction based on news article summarization can effectively outperform the prediction based on full-length article on both validation and independent testing sets.

show abstract

“…Finally, conclusion for this paper is in Section 6. Figure 1 shows the main summarization approaches [8]. There are two categories of summarization: abstract-based and extract-based.…”

Section: Introductionmentioning

confidence: 99%

Text Summarization Using FrameNet-Based Semantic Graph Model

Han

Hu³

et al. 2016

Scientific Programming

View full text Add to dashboard Cite

Text summarization is to generate a condensed version of the original document. The major issues for text summarization are eliminating redundant information, identifying important difference among documents, and recovering the informative content. This paper proposes a Semantic Graph Model which exploits the semantic information of sentence using FSGM. FSGM treats sentences as vertexes while the semantic relationship as the edges. It uses FrameNet and word embedding to calculate the similarity of sentences. This method assigns weight to both sentence nodes and edges. After all, it proposes an improved method to rank these sentences, considering both internal and external information. The experimental results show that the applicability of the model to summarize text is feasible and effective. Abstract Unsupervised Sentence classification Sentence ranking SVM HMM CRF Cluster-based Graph-based Supervised ManmadeSubmit your manuscripts at

show abstract

Document Summarization via Self-Present Sentence Relevance Model

Cited by 6 publications

References 16 publications

Text Summarization Based on Sentence Selection with Semantic Representation

Text Summarization Based on Sentence Selection with Semantic Representation

Does Summarization Help Stock Prediction? A News Impact Analysis

Text Summarization Using FrameNet-Based Semantic Graph Model

Contact Info

Product

Resources

About