PLPing Li

Ping Li

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ping Li has a total of 5 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A neural machine translation method based on split graph convolutional self-attention encoding

    by Fei Wan, Ping Li

    With the continuous advancement of deep learning technologies, neural machine translation (NMT) has emerged as a powerful tool for enhancing communication efficiency among the members of cross-language collaborative teams. Among the various available approaches, leveraging syntactic dependency relations to achieve enhanced translation performance has become a pivotal research direction. However, current studies often lack in-depth considerations of non-Euclidean spaces when exploring interword correlations and fail to effectively address the model complexity arising from dependency relation encoding. To address these issues, we propose a novel approach based on split graph convolutional self-attention encoding (SGSE), aiming to more comprehensively utilize syntactic dependency relationships while reducing model complexity. Specifically, we initially extract syntactic dependency relations from the source language and construct a syntax dependency graph in a non-Euclidean space. Subsequently, we devise split self-attention networks and syntactic semantic self-attention networks, integrating them into a unified model. Through experiments conducted on multiple standard datasets as well as datasets encompassing scenarios related to team collaboration and enterprise management, the proposed method significantly enhances the translation performance of the utilized model while effectively mitigating model complexity. This approach has the potential to effectively enhance communication among cross-language team members, thereby ameliorating collaborative efficiency.


  • Open Access

    Table 2: Statistics of the parallel sentence pairs in the different datasets.

    by Fei Wan, Ping Li

    With the continuous advancement of deep learning technologies, neural machine translation (NMT) has emerged as a powerful tool for enhancing communication efficiency among the members of cross-language collaborative teams. Among the various available approaches, leveraging syntactic dependency relations to achieve enhanced translation performance has become a pivotal research direction. However, current studies often lack in-depth considerations of non-Euclidean spaces when exploring interword correlations and fail to effectively address the model complexity arising from dependency relation encoding. To address these issues, we propose a novel approach based on split graph convolutional self-attention encoding (SGSE), aiming to more comprehensively utilize syntactic dependency relationships while reducing model complexity. Specifically, we initially extract syntactic dependency relations from the source language and construct a syntax dependency graph in a non-Euclidean space. Subsequently, we devise split self-attention networks and syntactic semantic self-attention networks, integrating them into a unified model. Through experiments conducted on multiple standard datasets as well as datasets encompassing scenarios related to team collaboration and enterprise management, the proposed method significantly enhances the translation performance of the utilized model while effectively mitigating model complexity. This approach has the potential to effectively enhance communication among cross-language team members, thereby ameliorating collaborative efficiency.

  • Open Access

    Table 7: Experimental comparison results obtained on team communication datasets.

    by Fei Wan, Ping Li

    With the continuous advancement of deep learning technologies, neural machine translation (NMT) has emerged as a powerful tool for enhancing communication efficiency among the members of cross-language collaborative teams. Among the various available approaches, leveraging syntactic dependency relations to achieve enhanced translation performance has become a pivotal research direction. However, current studies often lack in-depth considerations of non-Euclidean spaces when exploring interword correlations and fail to effectively address the model complexity arising from dependency relation encoding. To address these issues, we propose a novel approach based on split graph convolutional self-attention encoding (SGSE), aiming to more comprehensively utilize syntactic dependency relationships while reducing model complexity. Specifically, we initially extract syntactic dependency relations from the source language and construct a syntax dependency graph in a non-Euclidean space. Subsequently, we devise split self-attention networks and syntactic semantic self-attention networks, integrating them into a unified model. Through experiments conducted on multiple standard datasets as well as datasets encompassing scenarios related to team collaboration and enterprise management, the proposed method significantly enhances the translation performance of the utilized model while effectively mitigating model complexity. This approach has the potential to effectively enhance communication among cross-language team members, thereby ameliorating collaborative efficiency.

  • Open Access

    Figure 1: NMT model framework based on SGSE.

    by Fei Wan, Ping Li

    With the continuous advancement of deep learning technologies, neural machine translation (NMT) has emerged as a powerful tool for enhancing communication efficiency among the members of cross-language collaborative teams. Among the various available approaches, leveraging syntactic dependency relations to achieve enhanced translation performance has become a pivotal research direction. However, current studies often lack in-depth considerations of non-Euclidean spaces when exploring interword correlations and fail to effectively address the model complexity arising from dependency relation encoding. To address these issues, we propose a novel approach based on split graph convolutional self-attention encoding (SGSE), aiming to more comprehensively utilize syntactic dependency relationships while reducing model complexity. Specifically, we initially extract syntactic dependency relations from the source language and construct a syntax dependency graph in a non-Euclidean space. Subsequently, we devise split self-attention networks and syntactic semantic self-attention networks, integrating them into a unified model. Through experiments conducted on multiple standard datasets as well as datasets encompassing scenarios related to team collaboration and enterprise management, the proposed method significantly enhances the translation performance of the utilized model while effectively mitigating model complexity. This approach has the potential to effectively enhance communication among cross-language team members, thereby ameliorating collaborative efficiency.

  • Open Access

    Table 5: Experimental comparison among the results obtained in Chinese-English translation tasks with different splitting coefficients.

    by Fei Wan, Ping Li

    With the continuous advancement of deep learning technologies, neural machine translation (NMT) has emerged as a powerful tool for enhancing communication efficiency among the members of cross-language collaborative teams. Among the various available approaches, leveraging syntactic dependency relations to achieve enhanced translation performance has become a pivotal research direction. However, current studies often lack in-depth considerations of non-Euclidean spaces when exploring interword correlations and fail to effectively address the model complexity arising from dependency relation encoding. To address these issues, we propose a novel approach based on split graph convolutional self-attention encoding (SGSE), aiming to more comprehensively utilize syntactic dependency relationships while reducing model complexity. Specifically, we initially extract syntactic dependency relations from the source language and construct a syntax dependency graph in a non-Euclidean space. Subsequently, we devise split self-attention networks and syntactic semantic self-attention networks, integrating them into a unified model. Through experiments conducted on multiple standard datasets as well as datasets encompassing scenarios related to team collaboration and enterprise management, the proposed method significantly enhances the translation performance of the utilized model while effectively mitigating model complexity. This approach has the potential to effectively enhance communication among cross-language team members, thereby ameliorating collaborative efficiency.

  • Open Access

    Figure 2: Variations in the loss and BLEU values produced on the validation set.

    by Fei Wan, Ping Li

    With the continuous advancement of deep learning technologies, neural machine translation (NMT) has emerged as a powerful tool for enhancing communication efficiency among the members of cross-language collaborative teams. Among the various available approaches, leveraging syntactic dependency relations to achieve enhanced translation performance has become a pivotal research direction. However, current studies often lack in-depth considerations of non-Euclidean spaces when exploring interword correlations and fail to effectively address the model complexity arising from dependency relation encoding. To address these issues, we propose a novel approach based on split graph convolutional self-attention encoding (SGSE), aiming to more comprehensively utilize syntactic dependency relationships while reducing model complexity. Specifically, we initially extract syntactic dependency relations from the source language and construct a syntax dependency graph in a non-Euclidean space. Subsequently, we devise split self-attention networks and syntactic semantic self-attention networks, integrating them into a unified model. Through experiments conducted on multiple standard datasets as well as datasets encompassing scenarios related to team collaboration and enterprise management, the proposed method significantly enhances the translation performance of the utilized model while effectively mitigating model complexity. This approach has the potential to effectively enhance communication among cross-language team members, thereby ameliorating collaborative efficiency.

  • Open Access

    Table 4: Comparison among the BLEU scores of different models on public datasets.

    by Fei Wan, Ping Li

    With the continuous advancement of deep learning technologies, neural machine translation (NMT) has emerged as a powerful tool for enhancing communication efficiency among the members of cross-language collaborative teams. Among the various available approaches, leveraging syntactic dependency relations to achieve enhanced translation performance has become a pivotal research direction. However, current studies often lack in-depth considerations of non-Euclidean spaces when exploring interword correlations and fail to effectively address the model complexity arising from dependency relation encoding. To address these issues, we propose a novel approach based on split graph convolutional self-attention encoding (SGSE), aiming to more comprehensively utilize syntactic dependency relationships while reducing model complexity. Specifically, we initially extract syntactic dependency relations from the source language and construct a syntax dependency graph in a non-Euclidean space. Subsequently, we devise split self-attention networks and syntactic semantic self-attention networks, integrating them into a unified model. Through experiments conducted on multiple standard datasets as well as datasets encompassing scenarios related to team collaboration and enterprise management, the proposed method significantly enhances the translation performance of the utilized model while effectively mitigating model complexity. This approach has the potential to effectively enhance communication among cross-language team members, thereby ameliorating collaborative efficiency.

  • Open Access

    Table 6: BLEU scores produced by translation models on parallel sentence pairs with different sentence lengths.

    by Fei Wan, Ping Li

    With the continuous advancement of deep learning technologies, neural machine translation (NMT) has emerged as a powerful tool for enhancing communication efficiency among the members of cross-language collaborative teams. Among the various available approaches, leveraging syntactic dependency relations to achieve enhanced translation performance has become a pivotal research direction. However, current studies often lack in-depth considerations of non-Euclidean spaces when exploring interword correlations and fail to effectively address the model complexity arising from dependency relation encoding. To address these issues, we propose a novel approach based on split graph convolutional self-attention encoding (SGSE), aiming to more comprehensively utilize syntactic dependency relationships while reducing model complexity. Specifically, we initially extract syntactic dependency relations from the source language and construct a syntax dependency graph in a non-Euclidean space. Subsequently, we devise split self-attention networks and syntactic semantic self-attention networks, integrating them into a unified model. Through experiments conducted on multiple standard datasets as well as datasets encompassing scenarios related to team collaboration and enterprise management, the proposed method significantly enhances the translation performance of the utilized model while effectively mitigating model complexity. This approach has the potential to effectively enhance communication among cross-language team members, thereby ameliorating collaborative efficiency.

  • Open Access

    Table 3: Parameter settings for model training.

    by Fei Wan, Ping Li

    With the continuous advancement of deep learning technologies, neural machine translation (NMT) has emerged as a powerful tool for enhancing communication efficiency among the members of cross-language collaborative teams. Among the various available approaches, leveraging syntactic dependency relations to achieve enhanced translation performance has become a pivotal research direction. However, current studies often lack in-depth considerations of non-Euclidean spaces when exploring interword correlations and fail to effectively address the model complexity arising from dependency relation encoding. To address these issues, we propose a novel approach based on split graph convolutional self-attention encoding (SGSE), aiming to more comprehensively utilize syntactic dependency relationships while reducing model complexity. Specifically, we initially extract syntactic dependency relations from the source language and construct a syntax dependency graph in a non-Euclidean space. Subsequently, we devise split self-attention networks and syntactic semantic self-attention networks, integrating them into a unified model. Through experiments conducted on multiple standard datasets as well as datasets encompassing scenarios related to team collaboration and enterprise management, the proposed method significantly enhances the translation performance of the utilized model while effectively mitigating model complexity. This approach has the potential to effectively enhance communication among cross-language team members, thereby ameliorating collaborative efficiency.

  • Open Access

    Table 1: Software and hardware details for the simulations.

    by Fei Wan, Ping Li

    With the continuous advancement of deep learning technologies, neural machine translation (NMT) has emerged as a powerful tool for enhancing communication efficiency among the members of cross-language collaborative teams. Among the various available approaches, leveraging syntactic dependency relations to achieve enhanced translation performance has become a pivotal research direction. However, current studies often lack in-depth considerations of non-Euclidean spaces when exploring interword correlations and fail to effectively address the model complexity arising from dependency relation encoding. To address these issues, we propose a novel approach based on split graph convolutional self-attention encoding (SGSE), aiming to more comprehensively utilize syntactic dependency relationships while reducing model complexity. Specifically, we initially extract syntactic dependency relations from the source language and construct a syntax dependency graph in a non-Euclidean space. Subsequently, we devise split self-attention networks and syntactic semantic self-attention networks, integrating them into a unified model. Through experiments conducted on multiple standard datasets as well as datasets encompassing scenarios related to team collaboration and enterprise management, the proposed method significantly enhances the translation performance of the utilized model while effectively mitigating model complexity. This approach has the potential to effectively enhance communication among cross-language team members, thereby ameliorating collaborative efficiency.