paper-with-me

홈 › Papers

Human few-shot learning of compositional instructions

2019-01-14 · Brenden M. Lake, Tal Linzen, Marco Baroni

People learn in fast and flexible ways that have not been emulated by machines. Once a person learns a new verb "dax," he or she can effortlessly understand how to "dax twice," "walk and dax," or "dax vigorously." There have been striking recent improvements in machine learning for natural language processing, yet the best algorithms require vast amounts of experience and struggle to generalize new concepts in compositional ways. To better understand these distinctively human abilities, we study the compositional skills of people through language-like instruction learning tasks. Our results show that people can learn and use novel functional concepts from very few examples (few-shot learning), successfully applying familiar functions to novel inputs. People can also compose concepts in complex ways that go beyond the provided demonstrations. Two additional experiments examined the assumptions and inductive biases that people make when solving these tasks, revealing three biases: mutual exclusivity, one-to-one mappings, and iconic concatenation. We discuss the implications for cognitive modeling and the potential for building machines with more human-like language learning capabilities.

📄 PDF Abstract BibTeX arXiv:1901.04587

Code (2)

arkilpatel/compositional-generalization-seq2seq pytorch
jacobandreas/geca pytorch

Tasks

Few-Shot Learning

Similar Papers 제목 키워드 기반

Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement

2023-04-27 · Nikolaos Gkanatsios, Ayush Jain, Zhou Xian, Yunchu Zhang 외

Language is compositional; an instruction can express multiple relation constraints to hold among objects in a scene that a robot is tasked to rearrange. Our focus in this work is an instructable scene-rearranging framew…

Language ModelingLanguage ModellingLarge Language Model

Exploiting Language Instructions for Interpretable and Compositional Reinforcement Learning

2020-01-13 · Michiel van der Meer, Matteo Pirotta, Elia Bruni

In this work, we present an alternative approach to making an agent compositional through the use of a diagnostic classifier. Because of the need for explainable agents in automated decision processes, we attempt to inte…

ClassificationDiagnosticGeneral Classificationreinforcement-learning+2

Zero-Shot Semantic Parsing for Instructions

2019-11-20 · ACL 2019 7 · Ofer Givoli, Roi Reichart

We consider a zero-shot semantic parsing task: parsing instructions into compositional logical forms, in domains that were not seen during training. We present a new dataset with 1,390 examples from 7 application domains…

Semantic ParsingTriplet

On Conditional and Compositional Language Model Differentiable Prompting

2023-07-04 · Jonathan Pilault, Can Liu, Mohit Bansal, Markus Dreyer

Prompts have been shown to be an effective method to adapt a frozen Pretrained Language Model (PLM) to perform well on downstream tasks. Prompts can be represented by a human-engineered word sequence or by a learned cont…

Few-Shot LearningLanguage ModelingLanguage Modellingmodel+1

Hierarchical Decision Making by Generating and Following Natural Language Instructions

2019-06-03 · NeurIPS 2019 12 · Hengyuan Hu, Denis Yarats, Qucheng Gong, Yuandong Tian 외

We explore using latent natural language instructions as an expressive and compositional representation of complex actions for hierarchical decision making. Rather than directly selecting micro-actions, our agent first g…

Decision Making