Narjès Boufaden

Learn More
In this paper, we describe systems that were developed for the Open Performance Sub-Challenge of the INTERSPEECH 2009 Emotion Challenge. We participate in both two-class and fiveclass emotion detection. For the two-class problem, the best performance is obtained by logistic regression fusion of three systems. These systems use shortand long-term speech(More)
This paper presents a privacy compliance engine that monitors emails generated in an organization for violation of privacy policy of this organization. Our architecture includes four components: a domain knowledge defining the entities and private information we are dealing with, a pre-analysis component that extracts header information and segments the(More)
In this paper, we present a method for the semantic tagging of word chunks extracted from a written transcription of conversations. This work is part of an ongoing project for an information extraction system in the field of maritime Search And Rescue (SAR). Our purpose is to automatically annotate parts of texts with concepts from a SAR ontology. Our(More)
We study the problem of topic segmentation of manually transcribed speech in order to facilitate information extraction from dialogs. Our approach is based on a combination of multi-source knowledge modeled by hidden Markov models. We experiment with different combinations of linguistic-level cues on dialogs dealing with search and rescue missions. Results(More)
Breaching information privacy is a critical problem where legal remedies intervene only after the fact rather than prevent it. This paper presents an organizational privacy compliance engine that monitors outgoing emails to detect breaches of a privacy policy in an organization. The PEEP system employs email content analysis techniques to extract(More)
We present a new approach for the detection of negative versus non-negative emotions from Human-computer dialogs in the specific domain of call centers. We argue that it is possible to improve emotion detection without using additional information being linguistic or contextual. We show that no-answers are emotional salient words and that it is possible to(More)
  • 1