We present an oriented numerical summarizer algorithm, applied to producing automatic summaries of scientific documents in Organic Chemistry. We present its implementation named Yachs (Yet Another Chemistry Summarizer) that combines a specific document preprocessing with a sentence scoring method relying on the statistical properties of documents. We show that Yachs achieves the best results am...

Abstract. The revision of formal texts is a complex task and occurs in several areas. The objective of this work is to create a tool to support the revision of texts and promote studies in automatic correction of descriptive texts. We propose a reviewer for automatic identification of language deviations in formal descriptive texts using natural language processing techniques. A case study...

Automatic text summarization is the process of reducing the text content and retaining the important points of the document. Generally, there are two approaches for automatic text summarization: Extractive and Abstractive. The process of extractive based text summarization can be divided into two phases: pre-processing and processing. In this paper, we discuss some of the extractive based text ...

We describe improvements to our 2008 system that result in a top-performing summarization system. The motivating ideas are (1) improve sentence boundary detection to avoid damaging errors in preprocessing; (2) prune sentences that are unlikely to work well in a summary; (3) leverage sentence position to improve update summarization; (4) focus on high-precision sentence compression to improve re...

Drawing on the methodology and previous results of Rassi et al. (2014) on the automatic identification of Brazilian Portuguese proverbs, this paper reports on an extension of that experiment, but now focused on the identification of the European Portuguese proverbs and their variants. Based on a large collection of over 56 thousand Portuguese proverbs and their variants, a database of proverb t...

The automatic identification of direct and indirect discourses is a topic not yet explored in Natural Language Processing. We developed the DID system that when applied to children stories identifies the discourses, relative to the narrator (indirect discourse) or to the characters taking part in the story (direct discourse). This automation can be advantageous, namely when it is necessary to t...

The theoretical relation between preattentive processes and automatic processes is different in different approaches to attention and automaticity. In the modal view, automatic and preattentive processes are one and the same; automatic processing is preattentive. In recent views that treat automaticity as a memory phenomenon, automatic processing is postattentive. These views are described and ...

new field of endeavor. As with all new fields, the exact area it covers is not completely defined. Even the term languagedata processing is not yet generally accepted, although its use is increasing. The definition of the field of languagedata processing given here includes the application of any data-processing equipment to natural-language text—that is, not only the application of computing m...