Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER
Recent advances in prompt-based learning have shown strong results on few-shot text classification by using cloze-style templates. Similar attempts have been made on named entity recognition (NER) which manually design templates to predict entity types for every text span in a sentence. However, such methods may suffer from error propagation induced by entity span detection, high cost due to enumeration of all possible text spans, and omission of inter-dependencies among token labels in a sentence. Here we present a simple demonstration-based learning method for NER, which lets the input be prefaced by task demonstrations for in-context learning. We perform a systematic study on demonstration strategy regarding what to include (entity examples, with or without surrounding context), how to select the examples, and what templates to use. Results on in-domain learning and domain adaptation show that the model's performance in low-resource settings can be largely improved with a suitable demonstration strategy (e.g., a 4-17% improvement on 25 train instances). We also find that good demonstration can save many labeled examples and consistency in demonstration contributes to better performance.
Code (1)
Tasks
Domain AdaptationFew-Shot Text ClassificationIn-Context Learningnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERSentencetext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER
Recent advances in prompt-based learning have shown strong results on few-shot text classification by using cloze-style templates. Similar attempts have been made on named entity recognition (NER) which manually design t…
Domain AdaptationFew-Shot Text ClassificationIn-Context Learningnamed-entity-recognition+6500+ Times Faster Than Deep Learning (A Case Study Exploring Faster Methods for Text Mining StackOverflow)
Deep learning methods are useful for high-dimensional data and are becoming widely used in many areas of software engineering. Deep learners utilizes extensive computational power and can take a long time to train-- maki…
ClusteringCPUDeep LearningLearning Internal Representations (PhD Thesis)
Most machine learning theory and practice is concerned with learning a single task. In this thesis it is argued that in general there is insufficient information in a single task for a learner to generalise well and that…
Learning TheoryRepresentation LearningMeta-SGD: Learning to Learn Quickly for Few-Shot Learning
Few-shot learning is challenging for learning algorithms that learn each task in isolation and from scratch. In contrast, meta-learning learns from many related tasks a meta-learner that can learn a new task more accurat…
Few-Shot LearningMeta-Learningreinforcement-learningReinforcement Learning+1Machine Teaching for Bayesian Learners in the Exponential Family
What if there is a teacher who knows the learning goal and wants to design good training data for a machine learner? We propose an optimal teaching framework aimed at learners who employ Bayesian models. Our framework is…