CLLGMay 24, 2023

EXnet: Efficient In-context Learning for Data-less Text classification

arXiv:2305.14622v11 citations
Originality Incremental advance
AI Analysis

This addresses the need for efficient in-context learning in text classification, though it appears incremental as it builds on existing paradigms.

The paper tackles the problem of in-context learning for text classification by proposing EXnet, a model designed to perform this without limitations on example numbers, and shows that even a small 15M-parameter model generalizes to unseen tasks and domains.

Large pre-trained language models (PLMs) have made significant progress in encoding world knowledge and spawned a new set of learning paradigms including zero-shot, few-shot, and in-context learning. Many language tasks can be modeled as a set of prompts (for example, is this text about geography?) and language models can provide binary answers, i.e., Yes or No. There is evidence to suggest that the next-word prediction used by many PLMs does not align well with zero-shot paradigms. Therefore, PLMs are fine-tuned as a question-answering system. In-context learning extends zero-shot learning by incorporating prompts and examples, resulting in increased task accuracy. Our paper presents EXnet, a model specifically designed to perform in-context learning without any limitations on the number of examples. We argue that in-context learning is an effective method to increase task accuracy, and providing examples facilitates cross-task generalization, especially when it comes to text classification tasks. With extensive experiments, we show that even our smallest model (15M parameters) generalizes to several unseen classification tasks and domains.

Foundations

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

Your Notes