In this paper we present an active approach to annotate with lexical and semantic labels an Italian corpus of conversational human-human and Wizard-of-Oz dialogues. This procedure...
Christian Raymond, Kepa Joseba Rodriguez, Giuseppe...
We present a new active learning approach to incorporate
human feedback for on-line unusual event detection. In contrast to most
existing unsupervised methods that perform passiv...
In machine learning and computer vision, input signals are often filtered to increase data discriminability. For example, preprocessing face images with Gabor band-pass filters ...
This paper presents an adaptive learning framework for Phonetic Similarity Modeling (PSM) that supports the automatic construction of transliteration lexicons. The learning algori...
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...