Weighted hierarchical archetypal analysis for multi-document summarization

Canhasi, Ercan; Kononenko, Igor

doi:10.1016/j.csl.2015.11.004

Cited by 19 publications

(13 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have compared the performance of our system with the baselines in two situations: generic summarization and query-based summarization. To this end, we have used the two best participating systems of each dataset, the average of participating systems of each dataset, the best-proposed system in Wang et al (2016) and the suggested systems of Conroy, Schlesinger and O’Learry (2007), Toutanova et al (2007), Haghighi and Vanderwende (2009), Mason and Charniak (2011), He et al (2012), Cai and Li (2013), Li et al (2015), Canhasi and Kononenko (2016) and Cao et al (2016) as baselines.…”

Section: Experiments and Resultsmentioning

confidence: 99%

Extractive multi-document summarization based on textual entailment and sentence compression via knapsack problem

2018

View full text Add to dashboard Cite

By increasing the amount of data in computer networks, searching and finding suitable information will be harder for users. One of the most widespread forms of information on such networks are textual documents. So exploring these documents to get information about their content is difficult and sometimes impossible. Multi-document text summarization systems are an aid to producing a summary with a fixed and predefined length, while covering the maximum content of the input documents. This paper presents a novel method for multi-document extractive summarization based on textual entailment relations and sentence compression via formulating the problem as a knapsack problem. In this approach, sentences of documents are ranked according to the extended Tf-Idf method, then entailment scores of selected sentences are computed. Through these scores, the final score of each sentence is calculated. Finally, by decreasing the lengths of sentences via sentence compression, the problem has been solved by greedy and dynamic Programming approaches to the knapsack problem. Experiments on standard summarization datasets and evaluating the results based on the Rouge system show that the suggested method, according to the best of our knowledge, has increased F-measure of query-based summarization systems by two per cent and F-measure of general summarization systems by five per cent.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Extractive multi-document summarization based on textual entailment and sentence compression via knapsack problem

2018

View full text Add to dashboard Cite

show abstract

“…For the human genotype data studied by Huggins et al (2007), inferred archetypes are interpreted as representative populations for the measured genotypes. In computer vision, AA has for example been used by Bauckhage and Thurau (2009) to find archetypal images in large image collections or by Canhasi and Kononenko (2015) to perform the analogous task for large document collections. In combination with deep learning, archetypal style analysis (Wynen et al 2018) applies AA to learned image representations in order to realize artistic style manipulations.…”

Section: Related Workmentioning

confidence: 99%

Learning Extremal Representations with Deep Archetypal Analysis

et al. 2020

View full text Add to dashboard Cite

Archetypes represent extreme manifestations of a population with respect to specific characteristic traits or features. In linear feature space, archetypes approximate the data convex hull allowing all data points to be expressed as convex mixtures of archetypes. As mixing of archetypes is performed directly on the input data, linear Archetypal Analysis requires additivity of the input, which is a strong assumption unlikely to hold e.g. in case of image data. To address this problem, we propose learning an appropriate latent feature space while simultaneously identifying suitable archetypes. We thus introduce a generative formulation of the linear archetype model, parameterized by neural networks. By introducing the distance-dependent archetype loss, the linear archetype model can be integrated into the latent space of a deep variational information bottleneck and an optimal representation, together with the archetypes, can be learned end-to-end. Moreover, the information bottleneck framework allows for a natural incorporation of arbitrarily complex side information during training. As a consequence, learned archetypes become easily interpretable as they derive their meaning directly from the included side information. Applicability of the proposed method is demonstrated by exploring archetypes of female facial expressions while using multi-rater based emotion scores of these expressions as side information. A second application illustrates the exploration of the chemical space of small organic molecules. By using different kinds of side information we demonstrate how identified archetypes, along with their interpretation, largely depend on the side information provided.

show abstract

“…Lee et al (2003) argue that a term which occurs more frequently is not necessarily a good discriminator, and should be given less weight than one which occurs less frequently. In order to overcome this problem, PCA has been extensively used in summarization tasks whereby a summary is generated by extracting sentences that are likely to represent the main theme of a document (Bhatia & Jaiswal, 2015;Canhasi & Kononenko;Kogilavani, 2016). This is one of the basic geometric tools that are used to produce a lower number of the vectors within a corpus (Härdle & Simar, 2003;Jackson, 1991).…”

Section: Previous Workmentioning

confidence: 99%

Addressing the Problem of Coherence in Automatic Text Summarization: A Latent Semantic Analysis Approach

Omar¹

2017

IJEL

View full text Add to dashboard Cite

This article is concerned with addressing the problem of coherence in the automatic summarization of prose fiction texts. Despite the increasing advances within the summarization theory, applications and industry, many problems are still unresolved in relations to the applications of the summarization theory to literature. This can be in part attributed to the peculiar nature of literary texts where standard or typical summarization processes are not amenable for literature. This study, therefore, tends to bridge the gap between literature and summarization theory by proposing a summarization system that is based on more semantic-based approaches for extracting more meaningful and coherent summaries. Given that lack of coherence within summaries has its negative implications on understanding original texts; it follows that more effective methods should be developed in relation to the extraction of coherent summaries. In order to do this, a hybrid of methods including statistical (TF-IDF) and semantic (Latent Semantic Analysis LSA) methods were used to derive the most distinctive features and extract summaries from 10 English novellas. For evaluation purposes, both intrinsic and extrinsic methods are used for determining the quality of the extracted summaries. Results indicate that the integration of LSA into features extraction methods achieves better summarization performance outcomes in terms of coherence properties within the extracted summaries.

show abstract

Weighted hierarchical archetypal analysis for multi-document summarization

Cited by 19 publications

References 31 publications

Extractive multi-document summarization based on textual entailment and sentence compression via knapsack problem

Extractive multi-document summarization based on textual entailment and sentence compression via knapsack problem

Learning Extremal Representations with Deep Archetypal Analysis

Addressing the Problem of Coherence in Automatic Text Summarization: A Latent Semantic Analysis Approach

Contact Info

Product

Resources

About