ServiceNow AI Research

9

Competition exacerbates Language Drift
Competition exacerbates Language Drift
End-to-end interactive learning of dialogue systems has been all-but-abandoned in favour of other approaches using more labelled data, …
Machine Learning and the Evolution of Language (JCoLE Workshop),  2022.
Cite
Overcoming challenges in leveraging GANs for few-shot data augmentation
Overcoming challenges in leveraging GANs for few-shot data augmentation
In this paper, we explore the use of GAN-based few-shot data augmentation as a method to improve few-shot classification performance. …
Workshop at the Conference on Lifelong Learning Agents (CoLLAs),  2022.
PDF Cite
Scaling up ML-based Black-box Planning with Partial STRIPS Models
Scaling up ML-based Black-box Planning with Partial STRIPS Models
A popular approach for sequential decision-making is to perform simulator-based search guided with Machine Learning (ML) methods like …
Workshop at International Join Conference on Artificial Intelligence (IJCAI),  2022.
PDF Cite
Flaky Performances when Pre-Training on Relational Databases with a Plan for Future Characterization Efforts
Flaky Performances when Pre-Training on Relational Databases with a Plan for Future Characterization Efforts
We explore the downstream task performances for graph neural network (GNN) self-supervised learning (SSL) methods trained on subgraphs …
Workshop at the International Conference on Machine Learning (ICML),  2022.
PDF Cite
Unsupervised Model-based Pre-training for Data-efficient Reinforcement Learning from Pixels
Unsupervised Model-based Pre-training for Data-efficient Reinforcement Learning from Pixels
Reinforcement learning (RL) aims at autonomously performing complex tasks. To this end, a reward signal is used to steer the learning …
Workshop at the International Conference on Machine Learning (ICML),  2022.
PDF Cite
A Planning based Neural-Symbolic Approach for Embodied Instruction Following
A Planning based Neural-Symbolic Approach for Embodied Instruction Following
The ALFRED environment features embodied instruction following tasks in simulated home environments. However, end-to-end deep learning …
Workshop at the Conference on Computer Vision and Pattern Recognition (CVPR),  2022.
PDF Cite
Continual Learning with Foundation Models: An Empirical Study of Latent Replay
Continual Learning with Foundation Models: An Empirical Study of Latent Replay
Rapid development of large-scale pre-training has resulted in foundation models that can act as effective feature extractors on a …
Workshop at the Conference on Computer Vision and Pattern Recognition (CVPR),  2022.
PDF Cite
Scaling up ML-based Black-box Planning with Partial STRIPS Models
Scaling up ML-based Black-box Planning with Partial STRIPS Models
A popular approach for sequential decision-making is to perform simulator-based search guided with Machine Learning (ML) methods like …
ICAPS'22 Workshop on Reliable Data-Driven Planning and Scheduling,  2022.
PDF Cite
Data Augmentation for Intent Classification with Off-the-shelf Large Language Models
Data Augmentation for Intent Classification with Off-the-shelf Large Language Models
Data augmentation alleviates the problem of data scarcity when training language models (LMs) by generating new examples based on the …
Workshop at the Annual Meetings of the Association for Computational Linguistics (ACL),  2022.
PDF Cite
A Probabilistic Perspective on Reinforcement Learning via Supervised Learning
A Probabilistic Perspective on Reinforcement Learning via Supervised Learning
Reinforcement Learning via Supervised Learning (RvS) only uses supervised techniques to learn desirable behaviors from large datasets. …
Workshop at the International Conference on Learning Representations (ICLR),  2022.
PDF Cite