Advancing Multi-Criteria Chinese Word Segmentation Through Criterion Classification and Denoising

Anonymous

Abstract: Recent research on multi-criteria Chinese word segmentation (MCCWS) mainly focuses on building complex private structures, adding more handcrafted features, or introducing complex optimization processes.In this work, we show that through a simple yet elegant input-hint-based MCCWS model, we can achieve state-of-the-art (SoTA) performances on several datasets simultaneously.We further propose a novel criterion-denoising objective that hurts slightly on F1 score but acheives SoTA recall on out-of-vocabulary words.Our result establishes a simple yet strong baseline for future MCCWS research.

Paper Type: long

Research Area: Syntax: Tagging, Chunking and Parsing / ML