Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Information Extraction in Low-Resource Scenarios: Survey and Perspective

Shumin Deng, Yubo Ma, Ningyu Zhang, Yixin Cao, Bryan Hooi

TL;DR

This paper presents a review of neural approaches to low-resource IE from traditional and LLM-based perspectives, systematically organizing them into a fine-grained taxonomy, highlighting promising applications and delineating future research directions.

Abstract

Information Extraction (IE) seeks to derive structured information from unstructured texts, often facing challenges in low-resource scenarios due to data scarcity and unseen classes. This paper presents a review of neural approaches to low-resource IE from \emph{traditional} and \emph{LLM-based} perspectives, systematically categorizing them into a fine-grained taxonomy. Then we conduct empirical study on LLM-based methods compared with previous state-of-the-art models, and discover that (1) well-tuned LMs are still predominant; (2) tuning open-resource LLMs and ICL with GPT family is promising in general; (3) the optimal LLM-based technical solution for low-resource IE can be task-dependent. In addition, we discuss low-resource IE with LLMs, highlight promising applications, and outline potential research directions. This survey aims to foster understanding of this field, inspire new ideas, and encourage widespread applications in both academia and industry.

Information Extraction in Low-Resource Scenarios: Survey and Perspective

TL;DR

This paper presents a review of neural approaches to low-resource IE from traditional and LLM-based perspectives, systematically organizing them into a fine-grained taxonomy, highlighting promising applications and delineating future research directions.

Abstract

Information Extraction (IE) seeks to derive structured information from unstructured texts, often facing challenges in low-resource scenarios due to data scarcity and unseen classes. This paper presents a review of neural approaches to low-resource IE from \emph{traditional} and \emph{LLM-based} perspectives, systematically categorizing them into a fine-grained taxonomy. Then we conduct empirical study on LLM-based methods compared with previous state-of-the-art models, and discover that (1) well-tuned LMs are still predominant; (2) tuning open-resource LLMs and ICL with GPT family is promising in general; (3) the optimal LLM-based technical solution for low-resource IE can be task-dependent. In addition, we discuss low-resource IE with LLMs, highlight promising applications, and outline potential research directions. This survey aims to foster understanding of this field, inspire new ideas, and encourage widespread applications in both academia and industry.
Paper Structure (22 sections, 1 figure, 3 tables)

This paper contains 22 sections, 1 figure, 3 tables.

Table of Contents

  1. Introduction
  2. Preliminary on Low-resource IE
  3. Information Extraction
  4. Low-Resource Scenarios
  5. Taxonomy of Technical Solutions
  6. Traditional Methods
  7. Exploiting Higher-Resource Data
  8. Developing Stronger Data-Efficient Models
  9. Optimizing Data & Models Together
  10. LLM-Based Methods
  11. Direct Inference without Tuning
  12. Model Specialization with Tuning
  13. Empirical Study on Technical Solutions
  14. Setup
  15. Implementation Details
  16. ...and 7 more sections

Figures (1)

  • Figure 1: Taxonomy of low-resource IE methods. (We only list part of representative approaches, referring to the complete paper list$^{\text{1}}$ for more details.)