Compositionality and Generalization in Emergent Languages

• URL: http://arxiv.org/abs/2004.09124v1
• Date: Mon, 20 Apr 2020 08:30:14 GMT
• Title: Compositionality and Generalization in Emergent Languages
• Authors: Rahma Chaabouni, Eugene Kharitonov, Diane Bouchacourt, Emmanuel Dupoux, Marco Baroni
• Abstract summary: We study whether the language emerging in deep multi-agent simulations possesses a similar ability to refer to novel primitive combinations. We find no correlation between the degree of compositionality of an emergent language and its ability to generalize. The more compositional a language is, the more easily it will be picked up by new learners.
• Score: 42.68870559695238
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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{compositionality}. In this paper, we study whether the language emerging in deep multi-agent simulations possesses a similar ability to refer to novel primitive combinations, and whether it accomplishes this feat by strategies akin to human-language compositionality. Equipped with new ways to measure compositionality in emergent languages inspired by disentanglement in representation learning, we establish three main results. First, given sufficiently large input spaces, the emergent language will naturally develop the ability to refer to novel composite concepts. Second, there is no correlation between the degree of compositionality of an emergent language and its ability to generalize. Third, while compositionality is not necessary for generalization, it provides an advantage in terms of language transmission: The more compositional a language is, the more easily it will be picked up by new learners, even when the latter differ in architecture from the original agents. We conclude that compositionality does not arise from simple generalization pressure, but if an emergent language does chance upon it, it will be more likely to survive and thrive.

Related papers

• Analyzing The Language of Visual Tokens [48.62180485759458]
  We take a natural-language-centric approach to analyzing discrete visual languages. We show that higher token innovation drives greater entropy and lower compression, with tokens predominantly representing object parts. We also show that visual languages lack cohesive grammatical structures, leading to higher perplexity and weaker hierarchical organization compared to natural languages.
  arXiv  Detail & Related papers  (2024-11-07T18:59:28Z)
• A Complexity-Based Theory of Compositionality [53.025566128892066]
  In AI, compositional representations can enable a powerful form of out-of-distribution generalization. Here, we propose a formal definition of compositionality that accounts for and extends our intuitions about compositionality. The definition is conceptually simple, quantitative, grounded in algorithmic information theory, and applicable to any representation.
  arXiv  Detail & Related papers  (2024-10-18T18:37:27Z)
• The Role of Linguistic Priors in Measuring Compositional Generalization of Vision-Language Models [64.43764443000003]
  We identify two sources of visual-linguistic compositionality: linguistic priors and the interplay between images and texts. We propose a new metric for compositionality without such linguistic priors.
  arXiv  Detail & Related papers  (2023-10-04T12:48:33Z)
• On the Correspondence between Compositionality and Imitation in Emergent Neural Communication [1.4610038284393165]
  Our work explores the link between compositionality and imitation in a Lewis game played by deep neural agents. supervised learning tends to produce more average languages, while reinforcement learning introduces a selection pressure toward more compositional languages.
  arXiv  Detail & Related papers  (2023-05-22T11:41:29Z)
• Linking Emergent and Natural Languages via Corpus Transfer [98.98724497178247]
  We propose a novel way to establish a link by corpus transfer between emergent languages and natural languages. Our approach showcases non-trivial transfer benefits for two different tasks -- language modeling and image captioning. We also introduce a novel metric to predict the transferability of an emergent language by translating emergent messages to natural language captions grounded on the same images.
  arXiv  Detail & Related papers  (2022-03-24T21:24:54Z)
• Predicting emergent linguistic compositions through time: Syntactic frame extension via multimodal chaining [8.254139827478355]
  We develop a framework that exploits the cognitive mechanisms of chaining and multimodal knowledge to predict compositional expressions through time. We present the syntactic frame extension model (SFEM) that draws on the theory of chaining and knowledge from "percept", "concept", and "language" We show that multimodal SFEM predicts newly emerged verb syntax and arguments substantially better than competing models using purely linguistic or unimodal knowledge.
  arXiv  Detail & Related papers  (2021-09-10T03:42:07Z)
• The paradox of the compositionality of natural language: a neural machine translation case study [15.37696298313134]
  We re-instantiate three compositionality tests from the literature and reformulate them for neural machine translation (NMT) The results highlight two main issues: the inconsistent behaviour of NMT models and their inability to (correctly) modulate between local and global processing.
  arXiv  Detail & Related papers  (2021-08-12T17:57:23Z)
• Emergent Language Generalization and Acquisition Speed are not tied to Compositionality [31.6793931695019]
  We argue that these beneficial properties are only loosely connected to compositionality. In two experiments, we demonstrate that, depending on the task, non-compositional languages might show equal, or better, generalization performance and acquisition speed.
  arXiv  Detail & Related papers  (2020-04-07T14:10:27Z)
• A Benchmark for Systematic Generalization in Grounded Language Understanding [61.432407738682635]
  Humans easily interpret expressions that describe unfamiliar situations composed from familiar parts. Modern neural networks, by contrast, struggle to interpret novel compositions. We introduce a new benchmark, gSCAN, for evaluating compositional generalization in situated language understanding.
  arXiv  Detail & Related papers  (2020-03-11T08:40:15Z)
• Compositional Languages Emerge in a Neural Iterated Learning Model [27.495624644227888]
  compositionality enables natural language to represent complex concepts via a structured combination of simpler ones. We propose an effective neural iterated learning (NIL) algorithm that, when applied to interacting neural agents, facilitates the emergence of a more structured type of language.
  arXiv  Detail & Related papers  (2020-02-04T15:19:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.