• Publications
  • Influence
On the bayes-optimality of F-measure maximizers
TLDR
The F-measure, which has originally been introduced in information retrieval, is nowadays routinely used as a performance metric for problems such as binary classification, multi-label classification, and structured output prediction. Expand
  • 88
  • 7
  • PDF
A prototype for a conversational companion for reminiscing about images
TLDR
This paper describes an initial prototype of the Companions project (www.companions-project.org): the Senior Companion (SC), designed to be a platform to display novel approaches to:(1)The use of Information Extraction (IE) techniques to extract the content of incoming dialogue utterances after an ASR phase. Expand
  • 23
  • 3
  • PDF
A Nearest Neighbor Approach to Label Ranking based on Generalized Labelwise Loss Minimization
In this paper, we introduce a new (meta) learning technique for a preference learning problem called label ranking. As opposed to existing meta techniques, which mostly decompose the original problemExpand
  • 3
  • 3
  • PDF
A Simple Instance-Based Approach to Multilabel Classification Using the Mallows Model
Multilabel classification is an extension of conventional classification in which a single instance can be associated with multiple labels. Recent research has shown that, just like for standardExpand
  • 14
  • 1
  • PDF
Preference-based Evolutionary Direct Policy Search
TLDR
We present a novel approach to preference-based reinforcement learning, namely a preference- based variant of a direct policy search method based on evolutionary optimization. Expand
  • 11
  • 1
  • PDF
Preference-Based CBR: A Search-Based Problem Solving Framework
TLDR
Preference-based CBR is conceived as a case-based reasoning methodology in which problem solving experience is mainly represented in the form of contextualized preferences, namely preferences for candidate solutions in the context of a target problem to be solved. Expand
  • 8
  • 1
  • PDF
Predicting Long-Term Frequency Stability: Stochastic Oscillator Noise Analysis
High-performance frequency standards are affected by power-law noises and characterized by structure functions (i.e., variances). These variances with specified averaging time quantify the frequencyExpand
  • 1
Evaluating for Diversity in Question Generation over Text
TLDR
Generating diverse and relevant questions over text is a task with widespread applications. Expand
...
1
2
...