Unsupervised Translation of Emergent Communication
Emergent Communication (EC) provides a unique window into the language systems that emerge autonomously when agents are trained to jointly achieve shared goals. However, it is difficult to interpret EC and evaluate its relationship with natural languages (NL). This study employs unsupervised neural machine translation (UNMT) techniques to decipher ECs formed during referential games with varying task complexities, influenced by the semantic diversity of the environment. Our findings demonstrate UNMT's potential to translate EC, illustrating that task complexity characterized by semantic diversity enhances EC translatability, while higher task complexity with constrained semantic variability exhibits pragmatic EC, which, although challenging to interpret, remains suitable for translation. This research marks the first attempt, to our knowledge, to translate EC without the aid of parallel data.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityMachine TranslationTranslationSimilar Papers 제목 키워드 기반
Emergent Communication Pretraining for Few-Shot Machine Translation
While state-of-the-art models that rely upon massively multilingual pretrained encoders achieve sample efficiency in downstream applications, they still require abundant amounts of unlabelled text. Nevertheless, most of …
Machine TranslationNMTTransfer LearningTranslationConcept-Best-Matching: Evaluating Compositionality in Emergent Communication
Artificial agents that learn to communicate in order to accomplish a given task acquire communication protocols that are typically opaque to a human. A large body of work has attempted to evaluate the emergent communicat…
Learning Translations: Emergent Communication Pretraining for Cooperative Language Acquisition
In Emergent Communication (EC) agents learn to communicate with one another, but the protocols that they develop are specialised to their training community. This observation led to research into Zero-Shot Coordination (…
Imitation LearningLanguage AcquisitionEmergent Translation in Multi-Agent Communication
While most machine translation systems to date are trained on large parallel corpora, humans learn language in a different way: by being grounded in an environment and interacting with other humans. In this work, we prop…
Machine TranslationSentenceTranslationOn the Role of Emergent Communication for Social Learning in Multi-Agent Reinforcement Learning
Explicit communication among humans is key to coordinating and learning. Social learning, which uses cues from experts, can greatly benefit from the usage of explicit communication to align heterogeneous policies, reduce…
Multi-agent Reinforcement Learning