Extractive summarization using complex networks and syntactic dependency

The realization that statistical physics methods can be applied to analyze written texts represented as complex networks has led to several developments in natural language processing, including automatic summarization and evaluation of machine translation. Most importantly, so far only a few metrics of complex networks have been used and therefore there is ample opportunity to enhance the statistics-based methods as new measures of network topology and dynamics are created. In this paper, we employ for the first time the metrics betweenness, vulnerability and diversity to analyze written texts in Brazilian Portuguese. Using strategies based on diversity metrics, a better performance in automatic summarization is achieved in comparison to previous work employing complex networks. With an optimized method the Rouge score (an automatic evaluation method used in summarization) was 0.5089, which is the best value ever achieved for an extractive summarizer with statistical methods based on complex networks for Brazilian Portuguese. Furthermore, the diversity metric can detect keywords with high precision, which is why we believe it is suitable to produce good summaries. It is also shown that incorporating linguistic knowledge through a syntactic parser does enhance the performance of the automatic summarizers, as expected, but the increase in the Rouge score is only minor. These results reinforce the suitability of complex network methods for improving automatic summarizers in particular, and treating text in general. (C) 2011 Elsevier B.V. All rights reserved.

Contextual Reading and Metalinguistic Processing in Brazilian Portuguese: A Longitudinal Study

Metalinguistic skill is the ability to reflect upon language as an object of thought. Amongst metalinguistic skills, two seem to be associated with reading and spelling: morphological awareness and phonological awareness. Phonological awareness is the ability of reflecting upon the phonemes that compose words, and morphological awareness is the ability of reflecting upon the morphemes that compose the words. The latter seems to be particularly important for reading comprehension and contextual reading, as beyond phonological information, syntactic and semantic information are required. This study is set to investigate - with a longitudinal design - the relation between those abilities and contextual reading measured by the Cloze test. The first part of the study explores the relationship between morphological awareness tasks and Cloze scores through simple correlations and, in the second part, the specificity of such relationship was inquired using multiple regressions. The results give some support to the hypothesis that morphological awareness offers an independent contribution regarding phonological awareness to contextual reading in Brazilian Portuguese.

Structure-semantics interplay in complex networks and its effects on the predictability of similarity in texts

The classification of texts has become a major endeavor with so much electronic material available, for it is an essential task in several applications, including search engines and information retrieval. There are different ways to define similarity for grouping similar texts into clusters, as the concept of similarity may depend on the purpose of the task. For instance, in topic extraction similar texts mean those within the same semantic field, whereas in author recognition stylistic features should be considered. In this study, we introduce ways to classify texts employing concepts of complex networks, which may be able to capture syntactic, semantic and even pragmatic features. The interplay between various metrics of the complex networks is analyzed with three applications, namely identification of machine translation (MT) systems, evaluation of quality of machine translated texts and authorship recognition. We shall show that topological features of the networks representing texts can enhance the ability to identify MT systems in particular cases. For evaluating the quality of MT texts, on the other hand, high correlation was obtained with methods capable of capturing the semantics. This was expected because the golden standards used are themselves based on word co-occurrence. Notwithstanding, the Katz similarity, which involves semantic and structure in the comparison of texts, achieved the highest correlation with the NIST measurement, indicating that in some cases the combination of both approaches can improve the ability to quantify quality in MT. In authorship recognition, again the topological features were relevant in some contexts, though for the books and authors analyzed good results were obtained with semantic features as well. Because hybrid approaches encompassing semantic and topological features have not been extensively used, we believe that the methodology proposed here may be useful to enhance text classification considerably, as it combines well-established strategies. (c) 2012 Elsevier B.V. All rights reserved.

Identification of literary movements using complex networks to represent texts

The use of statistical methods to analyze large databases of text has been useful in unveiling patterns of human behavior and establishing historical links between cultures and languages. In this study, we identified literary movements by treating books published from 1590 to 1922 as complex networks, whose metrics were analyzed with multivariate techniques to generate six clusters of books. The latter correspond to time periods coinciding with relevant literary movements over the last five centuries. The most important factor contributing to the distinctions between different literary styles was the average shortest path length, in particular the asymmetry of its distribution. Furthermore, over time there has emerged a trend toward larger average shortest path lengths, which is correlated with increased syntactic complexity, and a more uniform use of the words reflected in a smaller power-law coefficient for the distribution of word frequency. Changes in literary style were also found to be driven by opposition to earlier writing styles, as revealed by the analysis performed with geometrical concepts. The approaches adopted here are generic and may be extended to analyze a number of features of languages and cultures.

Two-Item Sentence Comprehension by a Dog (Canis familiaris)

Syntax use by non-human animals remains a controversial issue. We present here evidence that a dog may respond to verbal requests composed of two independent terms, one referring to an object and the other to an action to be performed relative to the object. A female mongrel dog, Sofia, was initially trained to respond to action (point and fetch) and object (ball, key, stick, bottle and bear) terms which were then presented as simultaneous, combinatorial requests (e. g. ball fetch, stick point). Sofia successfully responded to object-action requests presented as single sentences, and was able to flexibly generalize her performance across different contexts. These results provide empirical evidence that dogs are able to extract the information contained in complex messages and to integrate it in directed performance, an ability which is shared with other linguistically trained animals and may represent a forerunner of syntactic functioning.

Analytical Processing Over XML and XLink

Current commercial and academic OLAP tools do not process XML data that contains XLink. Aiming at overcoming this issue, this paper proposes an analytical system composed by LMDQL, an analytical query language. Also, the XLDM metamodel is given to model cubes of XML documents with XLink and to deal with syntactic, semantic and structural heterogeneities commonly found in XML documents. As current W3C query languages for navigating in XML documents do not support XLink, XLPath is discussed in this article to provide features for the LMDQL query processing. A prototype system enabling the analytical processing of XML documents that use XLink is also detailed. This prototype includes a driver, named sql2xquery, which performs the mapping of SQL queries into XQuery. To validate the proposed system, a case study and its performance evaluation are presented to analyze the impact of analytical processing over XML/XLink documents.

Mini-Mental State Examination sentence writing among community-dwelling elderly adults in Brazil: text fluency and grammar complexity

Background: In normal aging, the decrease in the syntactic complexity of written production is usually associated with cognitive deficits. This study was aimed to analyze the quality of older adults' textual production indicated by verbal fluency (number of words) and grammatical complexity (number of ideas) in relation to gender, age, schooling, and cognitive status. Methods: From a probabilistic sample of community-dwelling people aged 65 years and above (n = 900), 577 were selected on basis of their responses to the Mini-Mental State Examination (MMSE) sentence writing, which were submitted to content analysis; 323 were excluded as they left the item blank or performed illegible or not meaningful responses. Education adjusted cut-off scores for the MMSE were used to classify the participants as cognitively impaired or unimpaired. Total and subdomain MMSE scores were computed. Results: 40.56% of participants whose answers to the MMSE sentence were excluded from the analyses had cognitive impairment compared to 13.86% among those whose answers were included. The excluded participants were older and less educated. Women and those older than 80 years had the lowest scores in the MMSE. There was no statistically significant relationship between gender, age, schooling, and textual performance. There was a modest but significant correlation between number of words written and the scores in the Language subdomain. Conclusions: Results suggest the strong influence of schooling and age over MMSE sentence performance. Failing to write a sentence may suggest cognitive impairment, yet, instructions for the MMSE sentence, i.e. to produce a simple sentence, may limit its clinical interpretation.

Probing the statistical properties of unknown texts: application to the Voynich manuscript

While the use of statistical physics methods to analyze large corpora has been useful to unveil many patterns in texts, no comprehensive investigation has been performed on the interdependence between syntactic and semantic factors. In this study we propose a framework for determining whether a text (e.g., written in an unknown alphabet) is compatible with a natural language and to which language it could belong. The approach is based on three types of statistical measurements, i.e. obtained from first-order statistics of word properties in a text, from the topology of complex networks representing texts, and from intermittency concepts where text is treated as a time series. Comparative experiments were performed with the New Testament in 15 different languages and with distinct books in English and Portuguese in order to quantify the dependency of the different measurements on the language and on the story being told in the book. The metrics found to be informative in distinguishing real texts from their shuffled versions include assortativity, degree and selectivity of words. As an illustration, we analyze an undeciphered medieval manuscript known as the Voynich Manuscript. We show that it is mostly compatible with natural languages and incompatible with random texts. We also obtain candidates for keywords of the Voynich Manuscript which could be helpful in the effort of deciphering it. Because we were able to identify statistical measurements that are more dependent on the syntax than on the semantics, the framework may also serve for text analysis in language-dependent applications.