Candidate Summary Research Articles

A New Metric of Validation for Automatic Text Summarization by Extraction

In this article, the author proposes a new metric of evaluation for automatic summaries of texts. In this case, the adaptation of the F-measure that generates a hybrid method of evaluating an automatic summary at the same time as both extrinsic and intrinsic. The article starts by studying the feasibility of adaptation of the F-measure for the evaluation of automatic summarization. After that, the author defines how to calculate the F-measure for a candidate summary. Text is presented with a term vector which can be either a word or a phrase, with a binary-weighted or occurrence. Finally, to determine to the exactitude of evaluation of the F-measure for automatic summarization by extraction calculates correlation with the ROUGE Evaluation.

Using Contextual Topic Model for a Query-Focused Multi-Document Summarizer

Oft-decried information overload is a serious problem that negatively impacts the comprehension of information in the digital age. Text summarization is a helpful process that can be used to alleviate this problem. With the aim of seeking a novel method to enhance the performance of multi-document summarization, this study proposes a novel approach to analyze the problem of multi-document summarization based on a mixture model, consisting of a contextual topic model from a Bayesian hierarchical topic modeling family for selecting candidate summary sentences, and a regression model in machine learning for generating the summary. By investigating hierarchical topics and their correlations with respect to the lexical co-occurrences of words, the proposed contextual topic model can determine the relevance of sentences more effectively, recognize latent topics, and arrange them hierarchically. The quantitative evaluation results from a practical application demonstrates that a system implementing this model can significantly improve the performance of summarization and make it comparable to state-of-the-art summarization systems.

Hybridization of Social Spiders and Extractions Techniques for Automatic Text Summaries

The authors propose a new multilayer approach for automatic text summaries. In the first layer, they use two techniques of extraction, one after the other: scoring of phrases, and similarity that aims to eliminate redundant phrases without losing the theme of the text. While the second layer aims to optimize the results of the previous layer by a meta-heuristic based on social spiders. Its objective function of the optimization is to maximize the sum of similarity between phrases of the candidate summary in order to keep the theme of the text, minimize the sum of scores in order to increase the summarization rate; this optimization also will give a candidate's summary where the order of the phrases changes compared to the original text. The third and final layer concerned in choosing a best summary from all candidates summaries generated by optimization layer, we opted for the technique of voting with a simple majority.

Combining Relevance Language Modeling and Clarity Measure for Extractive Speech Summarization

Extractive speech summarization, which purports to select an indicative set of sentences from a spoken document so as to succinctly represent the most important aspects of the document, has garnered much research over the years. In this paper, we cast extractive speech summarization as an ad-hoc information retrieval (IR) problem and investigate various language modeling (LM) methods for important sentence selection. The main contributions of this paper are four-fold. First, we explore a novel sentence modeling paradigm built on top of the notion of relevance, where the relationship between a candidate summary sentence and a spoken document to be summarized is discovered through different granularities of context for relevance modeling. Second, not only lexical but also topical cues inherent in the spoken document are exploited for sentence modeling. Third, we propose a novel clarity measure for use in important sentence selection, which can help quantify the thematic specificity of each individual sentence that is deemed to be a crucial indicator orthogonal to the relevance measure provided by the LM-based methods. Fourth, in an attempt to lessen summarization performance degradation caused by imperfect speech recognition, we investigate making use of different levels of index features for LM-based sentence modeling, including words, subword-level units, and their combination. Experiments on broadcast news summarization seem to demonstrate the performance merits of our methods when compared to several existing well-developed and/or state-of-the-art methods.

Exploiting Rhetorical Relations to Multiple Documents Text Summarization

Many of previous research have proven that the usage of rhetorical relations is capable to enhance many applications such as text summarization, question answering and natural language generation. This work proposes an approach that expands the benefit of rhetorical relations to address redundancy problem for cluster-based text summarization of multiple documents. We exploited rhetorical relations exist between sentences to group similar sentences into multiple clusters to identify themes of common information. The candidate summary were extracted from these clusters. Then, cluster-based text summarization is performed using Conditional Markov Random Walk Model to measure the saliency scores of the candidate summary. We evaluated our method by measuring the cohesion and separation of the clusters constructed by exploiting rhetorical relations and ROUGE score of generated summaries. The experimental result shows that our method performed well which shows promising potential of applying rhetorical relation in text clustering which benefits text summarization of multiple documents.

A reinforcement learning formulation to the complex question answering problem

We use extractive multi-document summarization techniques to perform complex question answering and formulate it as a reinforcement learning problem. Given a set of complex questions, a list of relevant documents per question, and the corresponding human generated summaries (i.e. answers to the questions) as training data, the reinforcement learning module iteratively learns a number of feature weights in order to facilitate the automatic generation of summaries i.e. answers to previously unseen complex questions. A reward function is used to measure the similarities between the candidate (machine generated) summary sentences and the abstract summaries. In the training stage, the learner iteratively selects the important document sentences to be included in the candidate summary, analyzes the reward function and updates the related feature weights accordingly. The final weights are used to generate summaries as answers to unseen complex questions in the testing stage. Evaluation results show the effectiveness of our system. We also incorporate user interaction into the reinforcement learner to guide the candidate summary sentence selection process. Experiments reveal the positive impact of the user interaction component on the reinforcement learning framework.

A New Biomimetic Method Based on the Power Saves of Social Bees for Automatic Summaries of Texts by Extraction

In this paper, the authors propose a new approach for automatic text summarization by extraction based on Saving Energy Function where the first step constitute to use two techniques of extraction: scoring of phrases, and similarity that aims to eliminate redundant phrases without losing the theme of the text. While the second step aims to optimize the results of the previous layer by the metaheuristic based on Bee Algorithm, the objective function of the optimization is to maximize the sum of similarity between phrases of the candidate summary in order to keep the theme of the text, minimize the sum of scores in order to increase the summarization rate, this optimization also will give a candidate's summary where the order of the phrases changes compared to the original text. The third and final layer aims to choose the best summary from the candidate summaries generated by bee optimization, the authors opted for the technique of voting with a simple majority.

Blending Sentence Optimization Weights of Unsupervised Approaches for Extractive Speech Summarization

Abstract This paper evaluates the performance of two unsupervised approaches, Maximum Marginal Relevance (MMR) and concept-based global optimization framework for speech summarization. Automatic summarization is very useful techniques that can help the users browse a large amount of data. This study focuses on automatic extractive summarization on multi-dialogue speech corpus. We propose improved methods by blending each unsupervised approach at sentence level. Sentence level information is leveraged to improve the linguistic quality of selected summaries. First, these scores are used to filter sentences for concept extraction and concept weight computation. Second, we pre-select a subset of candidate summary sentences according to their sentence weights. Last, we extend the optimization function to a joint optimization of concept and sentence weights to cover both important concepts and sentences. Our experimental results show that these methods can improve the system performance comparing to the concept-based optimization baseline for both human transcripts and ASR output. The best scores are achieved by combining all three approaches, which are significantly better than the baseline system.

Learning to rank-based gene summary extraction.

BackgroundIn recent years, the biomedical literature has been growing rapidly. These articles provide a large amount of information about proteins, genes and their interactions. Reading such a huge amount of literature is a tedious task for researchers to gain knowledge about a gene. As a result, it is significant for biomedical researchers to have a quick understanding of the query concept by integrating its relevant resources.MethodsIn the task of gene summary generation, we regard automatic summary as a ranking problem and apply the method of learning to rank to automatically solve this problem. This paper uses three features as a basis for sentence selection: gene ontology relevance, topic relevance and TextRank. From there, we obtain the feature weight vector using the learning to rank algorithm and predict the scores of candidate summary sentences and obtain top sentences to generate the summary.ResultsROUGE (a toolkit for summarization of automatic evaluation) was used to evaluate the summarization result and the experimental results showed that our method outperforms the baseline techniques.ConclusionsAccording to the experimental result, the combination of three features can improve the performance of summary. The application of learning to rank can facilitate the further expansion of features for measuring the significance of sentences.

Polityka rosyjska w Rzeczypospolitej w 1733 roku a kandydatura „Piasta”

Russian Policy in the Polish Commowealth in 1733 and a „Piast” Candidate (Summary)An agreement between families of Potoccy and Czartoryscy was an unexpected situation for Russia, nevertheless a new policy on the election of Polish king was arranged in the end of March, 1733. Russia decided to act together with its allies and to support candidate indicated by emperor – Portuguese heir don Emanuel. According to a treaty signed in 1732, if Austria and Prussia would not support Emanuel, there was considered to put some “Piast” on a Polish throne. In the article can be find precise information about acts and strategy made by Russian diplomats (among others: Jurij Liwen and Karl Gustaw i Friedrich Casimir von Löwenwolde) and Polish nobles’ reactions on those efforts, as well as Polish sympathies and alliances (including confederation against Stanilaw Leszczynski’s election).

Extracting easy to understand summary using differential evolution algorithm

This paper describes an optimization method based on differential evolution algorithm and its novel application to extract easy to understand summary for improving text readability. The idea is to improve the readability of the given text for reading difficulties using assistive summary. In order to extract easy to understand summary from the given text, an improved differential evolution algorithm is proposed. A new chromosome representation that considers ordering and similarity for extracting cohesive summary. Also a modified crossover operator and mutation operator are designed to generate potential offspring. The application of differential evolution algorithm for maximizing the average similarity and informative score in the candidate summary sentences is proposed. We applied the proposed algorithm in a corpus of educational text from ESL text books and in graded text. The results show that the summary generated using Differential Evolution algorithm performs better in accuracy, readability and lexical cohesion than existing techniques. The task based evaluation done by target audience also favors the significant effect of assistive summary in improving readability.

On the subjectivity of human-authored summaries

AbstractHuman-generated summaries are a blend of content and style, bound by the task restrictions, but are ‘subject to subjectiveness’ of the individuals summarising the documents. We study the impact of various facets that cause subjectivity such as brevity, information content and information coverage on human-authored summaries. The scale of subjectivity is quantitatively measured among various summaries using a question–answer-based cross-comprehension test. The test evaluates summaries for meaning rather than exact words based on questions, framed by the summary authors, derived from the summary. The number of questions that cannot be answered after reading the candidate summary reflects its subjectivity. The qualitative analysis of the outcome of the cross-comprehension test shows the relationship between the length of a summary, information content and nature of questions framed by the summary author.

Impact of ICP instability and hypotension on outcome in patients with severe head trauma

✓ This study describes the relationship between raised intracranial pressure (ICP), hypotension, and outcome from severe head injury. The study is based on information derived from the Traumatic Coma Data Bank where ICP records from a relatively large number of patients were available to help delineate the major factors influencing outcome. From the total data base of 1030 patients, 428 met minimum monitoring duration criteria for inclusion in the present analysis. Outcome was classified according to the Glasgow Outcome Scale score determined at 6 months postinjury. Arrays of comparably defined summary measures describing the patient's course were considered for ICP, blood pressure (BP), central perfusion pressure, and therapy intensity level. For instance, the array of ICP summary descriptors included the proportion of ICP readings greater than x, for x = 0 to 80 mm Hg by increments of 5 mm Hg. A total of 187 candidate summary descriptors were considered. A stepwise ordinal logistic regression was used to select the subset of candidate summary descriptors that best explained the 6-month outcome. As established previously, age, admission motor score, and abnormal pupils were each highly significant in explaining outcome. Beyond these factors, the proportion of hourly ICP readings greater than 20 mm Hg was next selected and was also highly significant in explaining outcome (p < 0.0001). In addition to the ICP factor, the cutoff point of 20 mm Hg was selected by the procedure as most indicative of outcome. With these four factors modeled, the next selected factor was the proportion of hourly BP readings less than 80 mm Hg. Again, the BP factor was highly significant in explaining outcome (p < 0.0001). As with the ICP factor, the BP cutoff point of 80 mm Hg was objectively selected as most indicative of outcome. In summary, the incidence of mortality and morbidity resulting from severe head trauma is strongly related to raised ICP and hypotension measured during the course of ICP management. Moreover, these ICP and BP factors provide a better indication of outcome than the similarly defined factors of central perfusion pressure or therapy intensity level.