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 …
evolutionary linguistics. Recently, with the development of deep learning techniques …
Compositional languages emerge in a neural iterated learning model
The principle of compositionality, which enables natural language to represent complex
concepts via a structured combination of simpler ones, allows us to convey an open-ended …
concepts via a structured combination of simpler ones, allows us to convey an open-ended …
Compositionality and generalization in emergent languages
Natural language allows us to refer to novel composite concepts by combining expressions
denoting their parts according to systematic rules, a property known as\emph …
denoting their parts according to systematic rules, a property known as\emph …
Emergent language generalization and acquisition speed are not tied to compositionality
E Kharitonov, M Baroni - arXiv preprint arXiv:2004.03420, 2020 - arxiv.org
Studies of discrete languages emerging when neural agents communicate to solve a joint
task often look for evidence of compositional structure. This stems for the expectation that …
task often look for evidence of compositional structure. This stems for the expectation that …
Defending compositionality in emergent languages
M Auersperger, P Pecina - arXiv preprint arXiv:2206.04751, 2022 - arxiv.org
Compositionality has traditionally been understood as a major factor in productivity of
language and, more broadly, human cognition. Yet, recently, some research started to …
language and, more broadly, human cognition. Yet, recently, some research started to …
Emergence of compositional language with deep generational transmission
Recent work has studied the emergence of language among deep reinforcement learning
agents that must collaborate to solve a task. Of particular interest are the factors that cause …
agents that must collaborate to solve a task. Of particular interest are the factors that cause …
Emergence of grounded compositional language in multi-agent populations
I Mordatch, P Abbeel - Proceedings of the AAAI conference on artificial …, 2018 - ojs.aaai.org
By capturing statistical patterns in large corpora, machine learning has enabled significant
advances in natural language processing, including in machine translation, question …
advances in natural language processing, including in machine translation, question …
Compositionality and capacity in emergent languages
Recent works have discussed the extent to which emergent languages can exhibit
properties of natural languages particularly learning compositionality. In this paper, we …
properties of natural languages particularly learning compositionality. In this paper, we …
Capacity, bandwidth, and compositionality in emergent language learning
Many recent works have discussed the propensity, or lack thereof, for emergent languages
to exhibit properties of natural languages. A favorite in the literature is learning …
to exhibit properties of natural languages. A favorite in the literature is learning …
[HTML][HTML] Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-off
Artificial learners often behave differently from human learners in the context of neural agent-
based simulations of language emergence and change. A common explanation is the lack …
based simulations of language emergence and change. A common explanation is the lack …