ReferentialGym: A Nomenclature and Framework for Language Emergence & Grounding in (Visual) Referential Games
This work aims to ease the entry barrier for researchers studying language emergence and grounding by providing a standardized framework and nomenclature.
This paper proposes a nomenclature to categorize existing research in language emergence and grounding, addressing variations in assumptions and constraints. It also introduces ReferentialGym, a PyTorch-based deep learning framework with baseline implementations of algorithms and metrics to facilitate research in this field.
Natural languages are powerful tools wielded by human beings to communicate information and co-operate towards common goals. Their values lie in some main properties like compositionality, hierarchy and recurrent syntax, which computational linguists have been researching the emergence of in artificial languages induced by language games. Only relatively recently, the AI community has started to investigate language emergence and grounding working towards better human-machine interfaces. For instance, interactive/conversational AI assistants that are able to relate their vision to the ongoing conversation. This paper provides two contributions to this research field. Firstly, a nomenclature is proposed to understand the main initiatives in studying language emergence and grounding, accounting for the variations in assumptions and constraints. Secondly, a PyTorch based deep learning framework is introduced, entitled ReferentialGym, which is dedicated to furthering the exploration of language emergence and grounding. By providing baseline implementations of major algorithms and metrics, in addition to many different features and approaches, ReferentialGym attempts to ease the entry barrier to the field and provide the community with common implementations.