Emergence of compositional language in communication through noisy channel
In this paper, we investigate how communication through a noisy channel can lead to the emergence of compositional language. Our approach is $\mbox{end-to-end}$, allows for different inductive biases on the agents’ architecture, and trains without periodical resets of the networks’ weights. This relaxes some of the assumptions in recently developed methods. The impact on the structure of the resulting language is shown in the context of signaling games. We also develop a new metric for measuring degree of compositionality.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agents
Since first introduced, computer simulation has been an increasingly important tool in evolutionary linguistics. Recently, with the development of deep learning techniques, research in grounded language learning has also…
Grounded language learningCatalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication
Communication is compositional if complex signals can be represented as a combination of simpler subparts. In this paper, we theoretically show that inductive biases on both the training framework and the data are needed…
Measuring non-trivial compositionality in emergent communication
Compositionality is an important explanatory target in emergent communication and language evolution. The vast majority of computational models of communication account for the emergence of only a very basic form of comp…
Emergence of Grounded Compositional Language in Multi-Agent Populations
By capturing statistical patterns in large corpora, machine learning has enabled significant advances in natural language processing, including in machine translation, question answering, and sentiment analysis. However,…
Machine TranslationQuestion AnsweringSentiment AnalysisTranslationEmergence of Numeric Concepts in Multi-Agent Autonomous Communication
With the rapid development of deep learning, most of current state-of-the-art techniques in natural langauge processing are based on deep learning models trained with argescaled static textual corpora. However, we human …
Deep Reinforcement LearningGrounded language learningReinforcement Learning