Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER

  title={Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER},
  author={Dong-Ho Lee and Mahak Agarwal and Akshen Kadakia and Takashi Shibuya and Jay Pujara and Xiang Ren},
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… 

Few-Shot Fine-Grained Entity Typing with Automatic Label Interpretation and Instance Generation

A novel framework for few-shot Fine-grained Entity Typing consisting of an entity type label interpretation module automatically learns to relate type labels to the vocabulary by jointly leveraging few- shot instances and the label hierarchy, and a type-based contextualized instance generator produces new instances based on given instances to enlarge the training set for better generalization.

Prompt-Based Metric Learning for Few-Shot NER

This work proposes a simple method to largely improve metric learning for NER by proposing a novel architecture to effectively combine multiple prompt-based representations designed to enhance label semantics.

Domain-Specific NER via Retrieving Correlated Samples

This paper draws correlated samples by the sparse BM25 retriever from large-scale in-domain unlabeled data and performs a training-free entity type calibrating by majority voting to simulate the human reasoning process and suggests enhancing NER models with correlated samples.

Robustness of Demonstration-based Learning Under Limited Data Scenario

This paper designs pathological demonstrations by gradually removing intuitively useful information from the standard ones to take a deep dive of the robustness of demonstration-based sequence labeling and shows that demonstrations composed of random tokens still make the model a better few-shot learner.

Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning

This work develops R ETRO P ROMPT with the motivation of decoupling knowledge from memorization to help the model strike a balance between generalization and memorization, which can reduce the reliance of language models on memorization and improve generalization for downstream tasks.

FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition

Results on several datasets show that the model-agnostic method significantly improves the performance of cross-domain NER tasks compared to previous state-of-the-art methods compared to the counterfactual data augmentation and prompt-tuning methods.

Few-shot Named Entity Recognition with Self-describing Networks

Self-describing Networks (SDNet) are designed, a Seq2Seq generation model which can universally describe mentions using concepts, automatically map novel entity types to concepts, and adaptively recognize entities on-demand.

Contrastive Demonstration Tuning for Pre-trained Language Models

Experimental results on 16 datasets illustrate that the proposed novel pluggable, extensible, and efficient approach named contrastive demon- 011 stration tuning, which is free of demonstration 012 sampling, can yield better performance.

DESED: Dialogue-based Explanation for Sentence-level Event Detection

This paper proposes a new paradigm, named dialogue-based explanation, to enhance sentence semantics for event detection, by explaining it through a consistent information-intensive dialogue, with the original event description as the start utterance.

Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructions

It is shown that annotation of just a few target- domain samples via active learning can be beneficial for transfer, but the impact diminishes with more annotation effort, and that not all transfer scenarios yield a positive gain, which seems related to the PLMs initial performance on the target-domain task.



Reordering Examples Helps during Priming-based Few-Shot Learning

This work introduces PERO (Prompting with Examples in the Right Order), where it is shown that PERO can learn to generalize efficiently using as few as 10 examples, in contrast to existing approaches.

Template-Based Named Entity Recognition Using BART

A template-based method for NER, treating NER as a language model ranking problem in a sequence-to-sequence framework, where original sentences and statement templates filled by candidate named entity span are regarded as the source sequence and the target sequence, respectively.

Making Pre-trained Language Models Better Few-shot Learners

The LM-BFF approach makes minimal assumptions on task resources and domain expertise, and hence constitutes a strong task-agnostic method for few-shot learning.

Few-Shot Named Entity Recognition: A Comprehensive Study

Three orthogonal schemes to improve the model generalization ability for few-shot settings are investigated: meta-learning to construct prototypes for different entity types, supervised pre-training on noisy web data to extract entity-related generic representations and self-training to leverage unlabeled in-domain data.

Learning Named Entity Tagger using Domain-Specific Dictionary

After identifying the nature of noisy labels in distant supervision, a novel, more effective neural model AutoNER is proposed with a new Tie or Break scheme and how to refine distant supervision for better NER performance is discussed.

Distantly Supervised NER with Partial Annotation Learning and Reinforcement Learning

This paper proposes a novel approach which can partially solve the above problems of distant supervision for NER, and applies partial annotation learning to reduce the effect of unknown labels of characters in incomplete and noisy annotations.

Calibrate Before Use: Improving Few-Shot Performance of Language Models

This work first estimates the model's bias towards each answer by asking for its prediction when given the training prompt and a content-free test input such as "N/A", and then fits calibration parameters that cause the prediction for this input to be uniform across answers.

Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference

This work introduces Pattern-Exploiting Training (PET), a semi-supervised training procedure that reformulates input examples as cloze-style phrases to help language models understand a given task.

TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition

The proposed model, Trigger Matching Network, jointly learns trigger representations and soft matching module with self-attention such that can generalize to unseen sentences easily for tagging, and is significantly more cost-effective than the traditional neural NER frameworks.

Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning

This paper finds empirically that the contextual representations computed on the retrieval-based input view, constructed through the concatenation of a sentence and its external contexts, can achieve significantly improved performance compared to the original input view based only on the sentence.