GÊNERO TEXTUAL E TIPOLOGIA TEXTUAL: COLOCAÇÕES SOB DOIS ENFOQUES TEÓRICOS7

Combining textual and non-textual features for e-mail importance estimation

In this work, we present a binary classification problem in which we aim to identify those email messages that the receiver will reply to. The future goal is to develop a tool that informs a knowledge worker which emails are likely to need a reply. The Enron corpus was used to extract training examples. We analysed the word n-grams that characterize the messages that the receiver replies to. Ad...

Textual Entailment

The task of Recognizing Textual Entailment (RTE) requires automated systems to identify when two spans of text share a common meaning -for example, that ``Alphaville Inc.'s attempted acquisition of Bauhaus led to a jump in both companies' stock prices'' entails ``Bauahaus' stock rose'', but not ``Alphaville acquired Bauhaus''. This general capability would be a solid proxy for Natural Language ...

Textual Entailment

Drawing about images: textual and non-textual interpretation

° full paper Context and Conditions This paper addresses a familiar situation from a novel point of view. The familiar situation has two aspects: (1) that writing about architecture and drawing architecture produces two different types of outcome that are difficult to reconcile; and (2) that drawing about architecture does not produce uniform results and those experts who are used to interpreti...

A New Textual/Non-Textual Classifier for Document Skew Correction

This work is supported by National Nature Science Foundation of China (69982005) and Projects of Development Plan of the State Key Foundation Search (G199803050703) Abstract: A robust approach is proposed for document skew detection. We use Fourier analysis and SVM to classify textual areas from non-textual areas of documents. We also propose a robust method to determine the skew angle from tex...