Jiwei Li, Jing Jiang, Shuming Shi, Yong Dai, Duyu Tang, Zhangyin Feng, Guoping Huang, Minghuan Tan
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
While GPT has become the de-facto method for text generation tasks, its application to pinyin input method remains unexplored. In this work, we make the first exploration to leverage Chinese GPT for pinyin input method. We find that a frozen GPT achieves state-of-the-art performance on perfect pinyin. However, the performance drops dramatically when the input includes abbreviated pinyin. A reason is that an abbreviated pinyin can be mapped to many perfect pinyin, which links to even larger number of Chinese characters. We mitigate this issue with two strategies, including enriching the context with pinyin and optimizing the training process to help distinguish homophones. To further facilitate the evaluation of pinyin input method, we create a dataset consisting of 270K instances from fifteen domains. Results show that our approach improves the performance on abbreviated pinyin across all domains. Model analysis demonstrates that both strategies contribute to the performance boost.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.00249")
get_code_for_paper("2203.00249")
have("2203.00249")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.00249.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.00249)
Connect an agent — have() is free.