Shuo Wen Jie Zi: Rethinking Dictionaries and Glyphs for Chinese Language Pre-training
This work addresses the challenge of improving semantics in Chinese language models for both modern and ancient text processing, though it is incremental as it builds on existing PLMs.
The paper tackles the problem of enhancing Chinese pre-trained language models' semantic understanding by incorporating dictionary knowledge and character glyph structure, resulting in consistent improvements across modern and ancient Chinese benchmarks and significant gains in few-shot ancient Chinese understanding.
We introduce CDBERT, a new learning paradigm that enhances the semantics understanding ability of the Chinese PLMs with dictionary knowledge and structure of Chinese characters. We name the two core modules of CDBERT as Shuowen and Jiezi, where Shuowen refers to the process of retrieving the most appropriate meaning from Chinese dictionaries and Jiezi refers to the process of enhancing characters' glyph representations with structure understanding. To facilitate dictionary understanding, we propose three pre-training tasks, i.e., Masked Entry Modeling, Contrastive Learning for Synonym and Antonym, and Example Learning. We evaluate our method on both modern Chinese understanding benchmark CLUE and ancient Chinese benchmark CCLUE. Moreover, we propose a new polysemy discrimination task PolyMRC based on the collected dictionary of ancient Chinese. Our paradigm demonstrates consistent improvements on previous Chinese PLMs across all tasks. Moreover, our approach yields significant boosting on few-shot setting of ancient Chinese understanding.