That Slepen Al the Nyght with Open Ye! Cross-era Sequence Segmentation with Switch-memory

TL;DR

This paper introduces CROSSWISE, a cross-era learning framework for Chinese word segmentation that employs a Switch-memory module to incorporate era-specific linguistic knowledge, improving performance across different historical texts.

Contribution

It presents a novel cross-era learning framework with a Switch-memory module for Chinese word segmentation, addressing diachronic language variation.

Findings

Significant performance improvements on four different era corpora

Effective integration of era-specific knowledge into neural networks

Demonstrated ability to handle diachronic linguistic gaps

Abstract

The evolution of language follows the rule of gradual change. Grammar, vocabulary, and lexical semantic shifts take place over time, resulting in a diachronic linguistic gap. As such, a considerable amount of texts are written in languages of different eras, which creates obstacles for natural language processing tasks, such as word segmentation and machine translation. Although the Chinese language has a long history, previous Chinese natural language processing research has primarily focused on tasks within a specific era. Therefore, we propose a cross-era learning framework for Chinese word segmentation (CWS), CROSSWISE, which uses the Switch-memory (SM) module to incorporate era-specific linguistic knowledge. Experiments on four corpora from different eras show that the performance of each corpus significantly improves. Further analyses also demonstrate that the SM can effectively integrate the knowledge of the eras into the neural network.