This paper presents the NLP Few-shot Gym, a repository of 160 diverse few-shot NLP tasks created from open-access NLP datasets and converted to a unified text-to-text format, and reveals that the few- shot learning ability on unseen tasks can be improved via an upstream learning stage using a set of seen tasks.
This paper develops a simple yet effective adaptation method for DS-trained models, bias adjustment, which updates models learned over the source domain with a label distribution estimated on the target domain, which achieves consistent performance gains on DS- trained models.
A novel Neural Execution Tree (NExT) framework to augment training data for text classification using NL explanations by transforming NL explanations into executable logical forms by semantic parsing, which substantially increases the coverage of each NL explanation.
This paper applies natural language processing (NLP) to effect semi-automated generation of protocol implementations from specification text to uncover ambiguous or under-specified sentences in specifications; once these are clarified by the author of the protocol specification, Sage can generate protocol code automatically.
This work proposes to refine a learned model by collecting humanprovided compositional explanations on the models’ failure cases by describing generalizable rules about spurious patterns in the explanation, and introduces a regularization term for feature interaction to support more complex human rationale in refining the model.
This paper extracts structured variables and rules from explanations and compose neural module teachers that annotate instances for training downstream MRC models, and uses learnable neural modules and soft logic to handle linguistic variation and overcome sparse coverage.
This work introduces LEAN-LIFE, a web-based, Label-Efficient AnnotatioN framework for sequence labeling and classification tasks, with an easy-to-use UI that not only allows an annotator to provide the needed labels for a task but also enables LearnIng From Explanations for each labeling decision.
HYPTER is introduced, a framework that improves zero-shot transferability by training a hypernetwork to generate task-specific adapters from task descriptions, and greatly reduces the number of parameters by using light-weight adapters.
This paper investigates the effects of using heuristic, directly supervised, and meta-learned MLM policies for intermediate pretraining, on eight selected tasks across three categories (closed-book QA, knowledgeintensive language tasks, and abstractive summarization).
This paper aims to learn the optimal masking strategy for the intermediate pretraining stage, and first train the masking policy to extract spans that are likely to be tested, using supervision from the downstream task itself, then deploy the learned policy during intermediate pre-training.