반응형 페이퍼572 [2023-10-24] 오늘의 자연어처리 Benchmarking and Improving Text-to-SQL Generation under Ambiguity Abstract:Research in Text-to-SQL conversion has been largely benchmarked against datasets where each text query corresponds to one correct SQL. However, natural language queries over real-life databases frequently involve significant ambiguity about the intended SQL due to overlapping schema names and multiple confusing relationsh.. 2023. 10. 24. [2023-10-23] 오늘의 자연어처리 Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models Abstract:Parameter-shared pre-trained language models (PLMs) have emerged as a successful approach in resource-constrained environments, enabling substantial reductions in model storage and memory costs without significant performance compromise. However, it is important to note that parameter sha.. 2023. 10. 23. [2023-10-22] 오늘의 자연어처리 Are Structural Concepts Universal in Transformer Language Models? Towards Interpretable Cross-Lingual Generalization Abstract:Large language models (LLMs) have exhibited considerable cross-lingual generalization abilities, whereby they implicitly transfer knowledge across languages. However, the transfer is not equally successful for all languages, especially for low-resource ones, which poses a.. 2023. 10. 22. [2023-10-21] 오늘의 자연어처리 Representing and Computing Uncertainty in Phonological Reconstruction Abstract:Despite the inherently fuzzy nature of reconstructions in historical linguistics, most scholars do not represent their uncertainty when proposing proto-forms. With the increasing success of recently proposed approaches to automating certain aspects of the traditional comparative method, the formal representation of pr.. 2023. 10. 21. 이전 1 ··· 17 18 19 20 21 22 23 ··· 143 다음 반응형