paper-with-me

홈 › Papers

Continual adaptation for efficient machine communication

2019-11-22 · CONLL 2020 · Robert D. Hawkins, Minae Kwon, Dorsa Sadigh, Noah D. Goodman

To communicate with new partners in new contexts, humans rapidly form new linguistic conventions. Recent neural language models are able to comprehend and produce the existing conventions present in their training data, but are not able to flexibly and interactively adapt those conventions on the fly as humans do. We introduce an interactive repeated reference task as a benchmark for models of adaptation in communication and propose a regularized continual learning framework that allows an artificial agent initialized with a generic language model to more accurately and efficiently communicate with a partner over time. We evaluate this framework through simulations on COCO and in real-time reference game experiments with human partners.

📄 PDF Abstract BibTeX arXiv:1911.09896

Code (1)

hawkrobe/continual-adaptation 공식 구현 pytorch

Tasks

Continual LearningLanguage ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Continual adaptation for efficient machine communication

2019-05-16 · ICML Workshop AMTL 2019 6 · Anonymous

To communicate with new partners in new contexts, humans rapidly form new linguistic conventions. Recent language models trained with deep neural networks are able to comprehend and produce the existing conventions prese…

Continual LearningLanguage ModelingLanguage Modelling

Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain Adaptation

2022-08-10 · Findings (NAACL) 2022 7 · Zhijing Wu, Hua Xu, Jingliang Fang, Kai Gao

Continual Machine Reading Comprehension aims to incrementally learn from a continuous data stream across time without access the previous seen data, which is crucial for the development of real-world MRC systems. However…

Domain AdaptationIncremental LearningMachine Reading ComprehensionReading Comprehension

SPD-CFL: Stepwise Parameter Dropout for Efficient Continual Federated Learning

2024-05-15 · Yuning Yang, Han Yu, Chuan Sun, Tianrun Gao 외

Federated Learning (FL) is a collaborative machine learning paradigm for training models on local sensitive data with privacy protection. Pre-trained transformer-based models have emerged as useful foundation models (FMs…

Continual LearningFederated Learningparameter-efficient fine-tuningTransfer Learning

ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation

2023-06-07 · Jiaming Liu, Senqiao Yang, Peidong Jia, Renrui Zhang 외

Since real-world machine systems are running in non-stationary environments, Continual Test-Time Adaptation (CTTA) task is proposed to adapt the pre-trained model to continually changing target domains. Recently, existin…

Test-time Adaptation

Continual Domain Adaptation for Machine Reading Comprehension

2020-08-25 · Lixin Su, Jiafeng Guo, Ruqing Zhang, Yixing Fan 외

Machine reading comprehension (MRC) has become a core component in a variety of natural language processing (NLP) applications such as question answering and dialogue systems. It becomes a practical challenge that an MRC…

Continual LearningDomain AdaptationMachine Reading ComprehensionQuestion Answering+1