GUIDE: Generative Unsupervised Chinese Query Correction via Phonetic and Visual Shared-ID Encoding
A generative unsupervised framework for CQC based on a confuse-then-clarify paradigm that encodes phonetically or visually confusable characters with shared-IDs and reconstructs the original query with an encoder--decoder architecture, which constrains correction to plausible confusion neighborhoods while learning from...
Lei Yang, Bin-Bin Huang, Jiyang Tan et al.
· 0 citations