Research ArticleOpen accessIn the keywordsTopic-Transformer for Document-Level Language UnderstandingOumaima Hourrane, El Habib BenlahmarAs long as natural language processing applications are considered prediction problems with insufficient context, usually referred to as a single sentence or paragraph, this does not reveal how humans perceive natural language. When reading a text, humans are sensitive to much more context, such as the rest or other relevant documents. This study focuses on simultaneously capturing syntax and global … …Journal of Computer Science, Vol. 18, Issue 1 · 22 Jan 2022 · 6,616 accessesView PDFCite
Research ArticleOpen accessIn the abstractHybrid Deep Learning Model for Evaluating Subjective Answers Based on Semantic Textual SimilaritySiddhesh Kudtarkar, Kavita ShirsatSubjective answer evaluation requires accurately identifying semantic similarities between student and reference responses. This study introduces a Hybrid Deep Learning Model (HDLM) that integrates CNN, GRU, and LSTM architectures to assess Semantic Textual Similarity (STS) more effectively. The HDLM employs two parallel branches-CNN-GRU and CNN-LSTM to capture both local syntactic features and long-range contextual dependencies, followed by Manhattan distance for … …Journal of Computer Science, Vol. 22, Issue 4 · 7 Apr 2026 · 1,690 accessesView PDFCite