BEAT-o-matic: a baseline for learning behavior expressions from utterances
نویسندگان
چکیده
In the context of human-robot dialogue, we consider the problem of annotating utterances with non-verbal behaviour. We argue for the need of a data-driven approach, that could learn those behaviours. As a first step we propose to replicate the results obtained by the current state-of-the-art, the rule-based system BEAT. Our proposed baseline, based on multi-label logistic regression with some simple features show that there is still more work needed for such an approach to produce satisfactory results. However, analyzing the results in more details reveal that for some behaviours such a simple model might already be good enough.
منابع مشابه
Using Collaborative Filtering to Predict User Utterances in Dialogue
This paper proposes using collaborative filtering, a technique for using other users’ information to model the behavior of a certain user, to predict users’ evaluative expressions for entities in dialogue. Previous studies have found that inducing users’ empathic utterances towards systems can improve user satisfaction. Predicting what users may utter and communicating this information in advan...
متن کاملExploring EFL Learners’ Use of Formulaic Sequences in Pragmatically Focused Role-play Tasks
Communicative language use largely entails regular patterns consisting of pre-constructed phrases or sequences. These sequences have been examined by many researchers to find the situation-based formulas which may help L2 learners follow a possibly more target-like speaking system. This study, therefore, explored two categories of formulaic expressions including speech formulas and situation-bo...
متن کاملA Mapping-Based Approach for General Formal Human Computer Interaction Using Natural Language
We consider the problem of mapping natural language written utterances expressing operational instructions1 to formal language expressions, applied to French and the R programming language. Developing a learning operational assistant requires the means to train and evaluate it, that is, a baseline system able to interact with the user. After presenting the guidelines of our work, we propose a m...
متن کاملEnabling a user to specify an item at any time during system enumeration - item identification for barge-in-able conversational dialogue systems
In conversational dialogue systems, users prefer to speak at any time and to use natural expressions. We have developed an Independent Component Analysis (ICA) based semi-blind source separation method, which allows users to barge-in over system utterances at any time. We created a novel method from timing information derived from barge-in utterances to identify one item that a user indicates d...
متن کاملPaper ST-13 The Lag-o-Matic: An Improved Method for Selecting the Lag Structure of Multiple Predictor Variables in the Absence of Theory
In applied econometrics, theory generally determines the appropriate lag of each independent (i.e., predictor) variable in a time series regression model. But, how does one determine the lag structure of each predictor variable without theory? Various schemes exist, but—without theory--variable-by-variable lag selection can be a daunting task that usually results in a timeintensive, “trial and ...
متن کامل