Interactive Relational Reinforcement Learning of Concept Semantics (Extended Abstract)

We propose a novel approach to the machine learning of formal word sense, learned in interaction with human users using a new form of Relational Reinforcement Learning. The envisaged main application area of our framework is human-machine communication, where a software agent or robot needs to understand concepts used by human users (e.g., in Natural Language Processing, HCI or Information Retrieval). In contrast to traditional approaches to the machine learning and disambiguation of word meaning, our framework focuses on the interactive learning of concepts in a dialogue with the user and on the integration of rich formal background knowledge and dynamically adapted policy constraints in the learning process, which makes our approach suitable for dynamic interaction environments with varying word usage contexts.

[1]  Claude Sammut,et al.  Hierarchical reinforcement learning: a hybrid approach , 2004 .

[2]  Achim Rettinger,et al.  Interactive relational reinforcement learning of concept semantics , 2014, Machine Learning.

[3]  Ben Taskar,et al.  Reinforcement Learning in Relational Domains: A Policy-Language Approach , 2007 .

[4]  Heriberto Cuayáhuitl,et al.  Hierarchical Reinforcement Learning for Spoken Dialogue Systems , 2009 .

[5]  Lucia Specia,et al.  Learning Expressive Models for Word Sense Disambiguation , 2007, ACL.

[6]  Kurt Driessens,et al.  Relational Reinforcement Learning , 1998, Machine-mediated learning.

[7]  Céline Rouveirol,et al.  Relational TD Reinforcement Learning , 2008 .

[8]  Oliver Lemon,et al.  Reinforcement Learning for Adaptive Dialogue Systems - A Data-driven Methodology for Dialogue Management and Natural Language Generation , 2011, Theory and Applications of Natural Language Processing.

[9]  Saso Dzeroski,et al.  Integrating Guidance into Relational Reinforcement Learning , 2004, Machine Learning.

[10]  Roberto Navigli,et al.  Word sense disambiguation: A survey , 2009, CSUR.

[11]  R. T. Kuate.  Hierarchical reinforcement learning for trading agents , 2016 .

[12]  Raymond J. Mooney,et al.  Panning for gold: finding relevant semantic content for grounded language learning , 2011, MLSLP.

[13]  Luc Steels,et al.  Grounding symbols through evolutionary language games , 2002 .

[14]  Joohyung Lee,et al.  Circumscriptive Event Calculus as Answer Set Programming , 2009, IJCAI.

[15]  W. B. Knox.  Augmenting Reinforcement Learning with Human Feedback , 2011 .

[16]  Paul R. Cohen,et al.  Learning and Playing in Wubble World , 2008, AIIDE.

[17]  Rada Mihalcea,et al.  Unsupervised Large-Vocabulary Word Sense Disambiguation with Graph-based Algorithms for Sequence Data Labeling , 2005, HLT.

[18]  Maurice Bruynooghe,et al.  Towards Informed Reinforcement Learning , 2004, ICML 2004.