Chinese Named Entity Recognition Augmented with Lexicon Memory

TL;DR

The paper introduces LEMON, a novel Chinese NER model that combines character and word features with lexicon memory, improving boundary detection and handling OOV words, achieving state-of-the-art results.

Contribution

It presents a new fragment-based model with lexicon memory that enhances Chinese NER by integrating position-dependent features and addressing OOV challenges.

Findings

LEMON outperforms previous models on four datasets.

Incorporating lexicon memory improves boundary detection.

Position-dependent features enhance entity classification.

Abstract

Inspired by a concept of content-addressable retrieval from cognitive science, we propose a novel fragment-based model augmented with a lexicon-based memory for Chinese NER, in which both the character-level and word-level features are combined to generate better feature representations for possible name candidates. It is observed that locating the boundary information of entity names is useful in order to classify them into pre-defined categories. Position-dependent features, including prefix and suffix are introduced for NER in the form of distributed representation. The lexicon-based memory is used to help generate such position-dependent features and deal with the problem of out-of-vocabulary words. Experimental results showed that the proposed model, called LEMON, achieved state-of-the-art on four datasets.