语法纠错模型的训练方法

Search documents
腾讯申请语法纠错模型的训练方法等相关专利,能提高语法纠错模型的纠错性能
Jin Rong Jie· 2025-08-23 06:18
Group 1 - Tencent Technology (Shenzhen) Co., Ltd. has applied for a patent titled "Training Method, Device, Electronic Equipment, and Storage Medium for Grammar Error Correction Model" with publication number CN120524948A, filed on February 2024 [1] - The patent application outlines a method for training a grammar error correction model, which includes training an initial model using a first information sample set based on the target language, and subsequently refining it with a second information sample set containing grammatical errors [1] - The method involves identifying error features associated with grammatical mistakes in the second information sample set and using these features along with sample labels to train the intermediate grammar correction model into a target grammar correction model [1] Group 2 - Tencent Technology (Shenzhen) Co., Ltd. was established in 2000 and is primarily engaged in software and information technology services, with a registered capital of 2 million USD [2] - The company has made investments in 15 enterprises and participated in 264 bidding projects, holding 5000 trademark records and 5000 patent records, along with 535 administrative licenses [2]