← Search

Lian Yu

2 accepted papers

2022

CoSPA: An improved masked language model with copy mechanism for Chinese spelling correction

UAI 2022poster

Existing BERT-based models for Chinese spelling correction (CSC) have three issues. 1) Bert tends to rectify a correct low-frequency collocation into a high-frequency one and leads to over-correcting. 2) It fails to completely detect phonic or morphological errors by the current learned similarity k…

Cited by 9SourcePDFScholar
2022

Lyra: A Benchmark for Turducken-Style Code Generation

IJCAI 2022poster

Recently, neural techniques have been used to generate source code automatically. While promising for declarative languages, these approaches achieve much poorer performance on datasets for imperative languages. Since a declarative language is typically embedded in an imperative language (i.e., the…