Extractive text summarization: can we use the same techniques for any text?

In this paper we address two issues. The first one analyzes whether the performance of a text summarization method depends on the topic of a document. The second one is concerned with how certain linguistic properties of a text may affect the performance of a number of automatic text summarization methods. For this we consider semantic analysis methods, such as textual entailment and anaphora resolution, and we study how they are related to proper noun, pronoun and noun ratios calculated over original documents that are grouped into related topics. Given the obtained results, we can conclude that although our first hypothesis is not supported, since it has been found no evident relationship between the topic of a document and the performance of the methods employed, adapting summarization systems to the linguistic properties of input documents benefits the process of summarization.

The role of statistical and semantic features in single-document extractive summarization

This paper reports on the further results of the ongoing research analyzing the impact of a range of commonly used statistical and semantic features in the context of extractive text summarization. The features experimented with include word frequency, inverse sentence and term frequencies, stopwords filtering, word senses, resolved anaphora and textual entailment. The obtained results demonstrate the relative importance of each feature and the limitations of the tools available. It has been shown that the inverse sentence frequency combined with the term frequency yields almost the same results as the latter combined with stopwords filtering that in its turn proved to be a highly competitive baseline. To improve the suboptimal results of anaphora resolution, the system was extended with the second anaphora resolution module. The present paper also describes the first attempts of the internal document data representation.

Prediction of blackwood wood and pulp quality parameters using NIR-PLS-R spectral modelling : wavenumber ranges and smoothing points

Só está disponível o resumo.

Biological lectures delivered at the Marine Biological Laboratory of Wood's Holl [sic].

1895

Time factors of differentially preserved wood in two calcitic concretions in Pennsylvanian black shale from Indiana / Bertram G. Woodland -- and Catherine K. Richardson --.

v.33:no.10(1975)

Benjamin Wood, AB, 1797

This folder contains an original (20.5 x 12 in.), a typewritten copy (14.75 x 8.5 in.), and a photostat copy (21.5 x 13.75 in.) of the diploma of Benjamin Wood.

Certificate of the sale of Cyrus' freight of wood, 1793 September 9

Accounting records related to the wood brought by the sloop between May and September 1793 on three slips of paper bound with thread. The last page contains a certification signed by William Winthrop on September 9, 1793 of the sale of wood in Charlestown.

Biological lectures delivered at the Marine Biological Laboratory of Wood's Holl [sic].

1899

Biological lectures delivered at the Marine Biological Laboratory of Wood's Holl [sic].

1896-1897

Biological lectures delivered at the Marine Biological Laboratory of Wood's Holl [sic].

1893

Biological lectures delivered at the Marine Biological Laboratory of Wood's Holl [sic].

1898

Biological lectures delivered at the Marine Biological Laboratory of Wood's Holl [sic].

1894

A software tool for accurate assessment of costs and CO2 emissions in wood transport using OpenStreetMap©

Costs and environmental impacts are key elements in forest logistics and they must be integrated in forest decision-making. The evaluation of transportation fuel costs and carbon emissions depend on spatial and non-spatial data but in many cases the former type of data are dicult to obtain. On the other hand, the availability of software tools to evaluate transportation fuel consumption as well as costs and emissions of carbon dioxide is limited. We developed a software tool that combines two empirically validated models of truck transportation using Digital Elevation Model (DEM) data and an open spatial data tool, specically OpenStreetMap©. The tool generates tabular data and spatial outputs (maps) with information regarding fuel consumption, cost and CO2 emissions for four types of trucks. It also generates maps of the distribution of transport performance indicators (relation between beeline and real road distances). These outputs can be easily included in forest decision-making support systems. Finally, in this work we applied the tool in a particular case of forest logistics in north-eastern Portugal