TL;DR
This work establishes the first transformer-based benchmark for role identification in human activity descriptions and provides a scalable foundation for advanced activity reasoning and knowledge extraction.
AVA is introduced, a systematic framework for evaluating whether embeddings distinguish logic-sensitive relational semantics in ontologies and knowledge graphs, and reveals a persistent gap between linguistic representation learning and ontology-level discrimination, challenging the assumption that strong NLP benchmark...
Compared to end-to-end classification models, this method of constructing an embedding space based on cross-level semantic metric learning enhances the ability to learn textual causality features and significantly reduces the dependency on annotated data.
A robust WSD model that integrates a bidirectional long shortterm memory network (BiLSTM) with an attention mechanism, specifically designed for Chinese patent texts is proposed, providing reliable support for knowledge mining and intelligent text processing in technical domains.
A GAT-BiLSTM fusion model that integrates dependency syntactic analysis with graph attention mechanisms and bidirectional long short-term memory networks improves translation fidelity and semantic consistency while exhibiting strong robustness for structurally complex inputs.
A layer-wise analysis indicates that surface-level features such as temporality and negation are captured more reliably than deeper semantic phenomena like quantification in large language models, highlighting the limited capacity of current LLMs to generate fully formal meaning representations.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
