CLAIJun 8, 2024

Fighting Against the Repetitive Training and Sample Dependency Problem in Few-shot Named Entity Recognition

arXiv:2406.05460v28 citations
Originality Incremental advance
AI Analysis

This work addresses efficiency and reliability issues in few-shot NER for NLP practitioners, offering an incremental improvement over existing methods.

The paper tackles the repetitive training and sample dependency problems in few-shot named entity recognition by introducing a pre-trained steppingstone span detector and using a large language model to set reliable entity-type referents, resulting in superior performance with fewer training steps and human-labeled data, outperforming strong baselines including ChatGPT in fine-grained settings.

Few-shot named entity recognition (NER) systems recognize entities using a few labeled training examples. The general pipeline consists of a span detector to identify entity spans in text and an entity-type classifier to assign types to entities. Current span detectors rely on extensive manual labeling to guide training. Almost every span detector requires initial training on basic span features followed by adaptation to task-specific features. This process leads to repetitive training of the basic span features among span detectors. Additionally, metric-based entity-type classifiers, such as prototypical networks, typically employ a specific metric that gauges the distance between the query sample and entity-type referents, ultimately assigning the most probable entity type to the query sample. However, these classifiers encounter the sample dependency problem, primarily stemming from the limited samples available for each entity-type referent. To address these challenges, we proposed an improved few-shot NER pipeline. First, we introduce a steppingstone span detector that is pre-trained on open-domain Wikipedia data. It can be used to initialize the pipeline span detector to reduce the repetitive training of basic features. Second, we leverage a large language model (LLM) to set reliable entity-type referents, eliminating reliance on few-shot samples of each type. Our model exhibits superior performance with fewer training steps and human-labeled data compared with baselines, as demonstrated through extensive experiments on various datasets. Particularly in fine-grained few-shot NER settings, our model outperforms strong baselines, including ChatGPT. We will publicly release the code, datasets, LLM outputs, and model checkpoints.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes