Search papers, labs, and topics across Lattice.
This paper introduces GUIDE, a generative unsupervised framework for Chinese query correction that addresses the limitations of supervised methods by leveraging phonetic and visual shared-ID encoding. By employing a confuse-then-clarify paradigm, GUIDE constrains the correction process to plausible neighborhoods, effectively mitigating the issue of intent drift in short queries. Experimental results demonstrate that GUIDE significantly outperforms existing baselines on both a large-scale dataset and through online A/B testing, enhancing correction quality and user engagement.
Unsupervised query correction can achieve superior performance by cleverly encoding phonetic and visual similarities, avoiding the pitfalls of intent drift.
Chinese query correction (CQC) is important for search and query recommendation on content platforms, but supervised methods rely on large annotated correction pairs that are costly to maintain as query vocabularies evolve. Unsupervised correction with language models is attractive, yet in the short-query setting, unconstrained generation often over-corrects ambiguous inputs toward high-frequency phrases, causing intent drift. We propose \textsc{GUIDE}, a generative unsupervised framework for CQC based on a confuse-then-clarify paradigm. \textsc{GUIDE} 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 unlabeled query streams. A time-decayed, query-frequency-weighted objective further supports adaptation to rapidly changing query vocabularies. Experiments on \textit{QSpell 250K} and a large-scale real-world dataset (\textit{KwaiSearch}) show that \textsc{GUIDE} consistently outperforms strong baselines, while online A/B testing further confirms gains in correction quality and downstream engagement.
