research
∙
08/08/2023
Hybrid Retrieval-Augmented Generation for Real-time Composition Assistance
Retrieval augmented models show promise in enhancing traditional languag...
share
research
∙
06/14/2023
Fed-ZERO: Efficient Zero-shot Personalization with Federated Mixture of Experts
One of the goals in Federated Learning (FL) is to create personalized mo...
research
∙
10/20/2022
Boosting Natural Language Generation from Instructions with Meta-Learning
Recent work has shown that language models (LMs) trained with multi-task...
research
∙
04/17/2022
Pathologies of Pre-trained Language Models in Few-shot Fine-tuning
Although adapting pre-trained language models with few examples has show...
research
∙
04/06/2022
Knowledge Infused Decoding
Pre-trained language models (LMs) have been shown to memorize a substant...
research
∙
11/04/2021
CLUES: Few-Shot Learning Evaluation in Natural Language Understanding
Most recent progress in natural language understanding (NLU) has been dr...
research
∙
09/15/2021
A Conditional Generative Matching Model for Multi-lingual Reply Suggestion
We study the problem of multilingual automated reply suggestions (RS) mo...
research
∙
09/09/2021
MetaXT: Meta Cross-Task Transfer between Disparate Label Spaces
Albeit the universal representational power of pre-trained language mode...
research
∙
08/28/2021
WALNUT: A Benchmark on Weakly Supervised Learning for Natural Language Understanding
Building quality machine learning models for natural language understand...
research
∙
06/03/2021
A Dataset and Baselines for Multilingual Reply Suggestion
Reply suggestion models help users process emails and chats faster. Prev...
research
∙
04/16/2021
MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning
The combination of multilingual pre-trained representations and cross-li...
research
∙
04/12/2021
Self-Training with Weak Supervision
State-of-the-art deep neural networks require large-scale labeled traini...
research
∙
05/26/2020
Learning with Weak Supervision for Email Intent Detection
Email remains one of the most frequently used means of online communicat...
research
∙
11/10/2019
Meta Label Correction for Learning with Weak Supervision
Leveraging weak or noisy supervision for building effective machine lear...
research
∙
06/15/2018
Stochastic WaveNet: A Generative Latent Variable Model for Sequential Data
How to model distribution of sequential data, including but not limited ...
research
∙
11/20/2017