Language interaction for inferring and learning of safety concepts
Prof. Dr. Stefan Wermter
- University of Plymouth
- University of Hertfordshire
Competence Area: Situation
bothe [at] informatik.uni-hamburg.de
Objectives and expected results
In humans the concepts of reasonable and safe actions can be taught directly via natural language. In this project we will develop an understanding of explicit information from dialogues in natural language to infer and learn safe and unsafe concepts. In a conversation, humans use changes in a dialogue to predict safety-critical situations and use them to react accordingly. We propose to use the same cues for safer human-robot interaction for early verbal detection of dangerous situations. To achieve this goal, we use different language features, such as sentiment and dialogue act. We developed the neural models that learn to predict the sentiment of next upcoming utterance and to recognize the dialogue act of that utterance. Currently, we aim to bind them in a way to achieve our primary goal.
Keywords: Natural Language Processing, Human-Robot Interaction, Sentiment Analysis, Dialogue Act Processing
Bothe, C., Weber, C., Magg, S., and Wermter, S. (2018).
A Context-based Approach for Dialogue Act Recognition using Simple Recurrent Neural Networks.
Proceedings of the Language Resources and Evaluation Conference (LREC-2018).
Bothe, C., Magg, S., Weber, C., and Wermter, S. (2017).
Dialogue-based Neural Learning to Estimate Sentiment of Next-upcoming Utterance.
Proceedings of 26th International Conference on Artificial Neural Networks (ICANN-2017).
Lakomkin, E., Bothe, C., and Wermter, S. (2017).
GradAscent at EmoInt-2017: Character- and Word-Level Recurrent Neural Network Models for Tweet Emotion Intensity Detection.
Proceedings of Workshop WASSA at EMNLP-2017.