Related papers: Should We Be Pre-training? An Argument for End-tas…
While neural networks are powerful function approximators, they suffer from catastrophic forgetting when the data distribution is not stationary. One particular formalism that studies learning under non-stationary distribution is provided…
Pre-training has exhibited notable benefits to downstream tasks by boosting accuracy and speeding up convergence, but the exact reasons for these benefits still remain unclear. To this end, we propose to quantitatively and explicitly…
Data privacy and security have become a non-negligible factor in load forecasting. Previous researches mainly focus on training stage enhancement. However, once the model is trained and deployed, it may need to `forget' (i.e., remove the…
In multi-task learning, a learner is given a collection of prediction tasks and needs to solve all of them. In contrast to previous work, which required that annotated training data is available for all tasks, we consider a new setting, in…
Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks. Previous work has shown that scaling the number of training…
Continuously learning to solve unseen tasks with limited experience has been extensively pursued in meta-learning and continual learning, but with restricted assumptions such as accessible task distributions, independently and identically…
Task-agnostic forms of data augmentation have proven widely effective in computer vision, even on pretrained models. In NLP similar results are reported most commonly for low data regimes, non-pretrained models, or situationally for…
In this paper, we propose a learning algorithm that enables a model to quickly exploit commonalities among related tasks from an unseen task distribution, before quickly adapting to specific tasks from that same distribution. We investigate…
Fine-tuning pre-trained language models for downstream tasks has become a norm for NLP. Recently it is found that intermediate training based on high-level inference tasks such as Question Answering (QA) can improve the performance of some…
We develop models to classify desirable reasoning revisions in argumentative writing. We explore two approaches -- multi-task learning and transfer learning -- to take advantage of auxiliary sources of revision data for similar tasks.…
This work shows that value-aware model learning, known for its numerous theoretical benefits, is also practically viable for solving challenging continuous control tasks in prevalent model-based reinforcement learning algorithms. First, we…
Some Transformer-based models can perform cross-lingual transfer learning: those models can be trained on a specific task in one language and give relatively good results on the same task in another language, despite having been pre-trained…
Reliable and effective multi-task learning is a prerequisite for the development of robotic agents that can quickly learn to accomplish related, everyday tasks. However, in the reinforcement learning domain, multi-task learning has not…
Recent work has found that multi-task training with a large number of diverse tasks can uniformly improve downstream performance on unseen target tasks. In contrast, literature on task transferability has established that the choice of…
Subword tokenization is a commonly used input pre-processing step in most recent NLP models. However, it limits the models' ability to leverage end-to-end task learning. Its frequency-based vocabulary creation compromises tokenization in…
Active learning (AL) is a widely-used training strategy for maximizing predictive performance subject to a fixed annotation budget. In AL one iteratively selects training examples for annotation, often those for which the current model is…
Meta-learning approaches have been proposed to tackle the few-shot learning problem.Typically, a meta-learner is trained on a variety of tasks in the hopes of being generalizable to new tasks. However, the generalizability on new tasks of a…
End-to-end text image translation (TIT), which aims at translating the source language embedded in images to the target language, has attracted intensive attention in recent research. However, data sparsity limits the performance of…
The primary paradigm for multi-task training in natural language processing is to represent the input with a shared pre-trained language model, and add a small, thin network (head) per task. Given an input, a target head is the head that is…
Loading models pre-trained on the large-scale corpus in the general domain and fine-tuning them on specific downstream tasks is gradually becoming a paradigm in Natural Language Processing. Previous investigations prove that introducing a…