Pre-trained language models enhanced parsers have achieved outstanding performance in rich-resource languages. Cross-lingual dependency parsing aims to learn useful knowledge from high-resource languages to alleviate data scarcity in low-resource languages. However, effectively reducing the syntactic structure distributional bias and excavating the commonalities among languages is the key challenge for cross-lingual dependency parsing. To address this issue, we propose novel dynamic syntactic feature filtering and injecting networks based on the typical shared-private model that employs one shared and two private encoders to separate source and target language features. Concretely, a Language-Specific Filtering Network (LSFN) on private encoders emphasizes helpful information and ignores the irrelevant or harmful parts of it from the source language. Meanwhile, a Language-Invariant Injecting Network (LIIN) on the shared encoder integrates the advantages of BiLSTM and improved Transformer encoders to transcend language boundaries, thus amplifying syntactic commonalities across languages. Experiments on seven benchmark datasets show that our model achieves an average absolute gain of 1.84 UAS and 3.43 LAS compared with the shared-private model. Comparative experiments validate that both LSFN and LIIN components are complementary in transferring beneficial knowledge from source to target languages. Detailed analyses highlight that our model can effectively capture linguistic commonalities and mitigate the effect of distributional bias, showcasing its robustness and efficacy.

Due to the strong representation capability of pre-trained language models, Chinese spelling correction models have significantly improved. However, pre-trained language models focus on contextualized information and treat all words equally, thus ignoring the entity information. In practical application, entity words are the most difficult part to handle in various artificial intelligence tasks, i.e., machine translation, optical character recognition, and automatic speech recognition. To address this issue, we first construct an entity-focused Chinese spelling correction (EFCSC) dataset , the first public spelling correction corpus to emphasize entity errors. Furthermore, we propose an entity knowledge injected language model (EKILM) designed for entity-focused spelling correction, which injects entity information into pre-trained language models, thus ensuring traditional spelling correction models pay more attention to entity words. Experiments on several benchmark datasets show that our proposed model outperforms all strong baseline models, leading to state-of-the-art results on all datasets. Extensive experiments and detailed analyses demonstrate that our proposed model enhances entity error correction ability without damaging the normal spelling correction performance. Our code and dataset will be released at https://github.com/DPloved/EFCSC to facilitate future research.