Learning Structured Representations of Entity Names using Active Learning and Weak Supervision

TL;DR

This paper introduces a novel framework combining active learning and weak supervision to efficiently learn high-quality structured representations of entity names from minimal labeled data, aiding tasks like normalization and variant generation.

Contribution

The paper proposes a new learning approach that effectively learns structured entity name representations with limited labeled examples, without relying on context or external knowledge.

Findings

High-quality models learned from around a dozen labeled examples

Framework outperforms traditional methods in low-data scenarios

Effective for entity normalization and variant generation tasks

Abstract

Structured representations of entity names are useful for many entity-related tasks such as entity normalization and variant generation. Learning the implicit structured representations of entity names without context and external knowledge is particularly challenging. In this paper, we present a novel learning framework that combines active learning and weak supervision to solve this problem. Our experimental evaluation show that this framework enables the learning of high-quality models from merely a dozen or so labeled examples.