The structure of verbal sequences analyzed with unsupervised learning techniques - Computer Science > Computation and LanguageReport as inadecuate




The structure of verbal sequences analyzed with unsupervised learning techniques - Computer Science > Computation and Language - Download this document for free, or read online. Document in PDF available to download.

Abstract: Data mining allows the exploration of sequences of phenomena, whereas oneusually tends to focus on isolated phenomena or on the relation between twophenomena. It offers invaluable tools for theoretical analyses and explorationof the structure of sentences, texts, dialogues, and speech. We report here theresults of an attempt at using it for inspecting sequences of verbs from Frenchaccounts of road accidents. This analysis comes from an original approach ofunsupervised training allowing the discovery of the structure of sequentialdata. The entries of the analyzer were only made of the verbs appearing in thesentences. It provided a classification of the links between two successiveverbs into four distinct clusters, allowing thus text segmentation. We givehere an interpretation of these clusters by applying a statistical analysis toindependent semantic annotations.



Author: Catherine Recanati LIPN, Nicoleta Rogovschi LIPN, Younès Bennani LIPN

Source: https://arxiv.org/







Related documents