Qi Yang

Legislative text translation requires unusually high fidelity because terminological substitutions, modal shifts, and discourse-level reformulations may alter rights, duties, or institutional meaning. While Large Language Models (LLMs) and multi-agent systems have advanced general-purpose translation, their probabilistic generation processes remain weakly aligned with the constrained interpretive conditions of statutory language. Existing agentic frameworks, which primarily rely on horizontal collaboration among peer agents, often improve fluency without providing sufficient vertical control over the layered structure of legal language. This paper proposes HL-Trans, a Hierarchical Control Framework for legislative translation that operationalizes fidelity through three progressively constrained layers: terminology anchoring, syntactic shaping, and discourse polishing. Rather than treating Skopos theory as a license for free functional adaptation, we reinterpret the legislative translation brief as a constrained functional objective: the target text should preserve legal concepts, deontic force, and institutional genre while remaining subject to expert human review. Experiments on a Chinese-English-Japanese legislative corpus show that HL-Trans improves terminology consistency, deontic modality preservation, and discourse conformity over strong LLM and multi-agent baselines. The analysis further identifies a “Gain-Interference-Rescue” pattern: terminology constraints first improve conceptual fidelity; syntactic constraints may temporarily reduce surface fluency while protecting legal force; and discourse-level polishing can restore readability without relaxing lower-level constraints. The results suggest that hierarchical control is a promising design principle for trustworthy legal translation, while also underscoring the continuing need for transparent resources, expert validation, and accountable human oversight.

Resumo: Diante do duplo impasse atual de “carnaval tecnológico” e “experiência superficial”, enfrentado pelos espaços de turismo cultural imersivo, este estudo propõe as seguintes contramedidas e sugestões: toma a “Unidade Corpo-Ambiente” como uma importante perspectiva ontológica e se centra nela, para realizar uma reconstrução profunda. Construindo um modelo analítico quadridimensional de “corporeidade-ambientalidade-interpenetrabilidade-criatividade”, isto serve tanto como complemento ao desprezo pela corporificação na teoria crítica espacial ocidental quanto como tradução desse conceito para aplicação prática. Este texto insiste, consistentemente, na reflexão teórica sobre a “Unidade Corpo-Ambiente”, permanecendo vigilante contra seus riscos de romantização ou assimilação pelo capital. Finalmente, este trabalho argumenta que o design espacial deve ser uma “habitação existencial” que transcende o espetáculo tecnológico - uma fusão profunda entre humanidade e natureza.

In response to the dual predicament of "technological carnival" and "superficial experience" currently faced by immersive cultural-tourism spaces, this study proposes the following countermeasures and suggestions: it takes "Body-Environment Unity" as an important ontological viewpoint and centers on it to conduct a deep reconstruction. By constructing a four-dimensional analytical model of "embodiment—environmentality—interpenetrability—creativity", this serves both as a supplement to the neglect of embodiment in Western spatial critique theory and as a translation of this concept into practical application. This study consistently insists on theoretical reflection on "Body-Environment Unity", remaining vigilant against its risks of romanticization or assimilation by capital. Finally, this study argues that spatial design should be an "existential dwelling" that transcends technological spectacle—a deep fusion between humanity and nature. Submission: 26/11/2025 – Decision: 23/12/2025 - Revision: 7/1/2026 – Publication: 20/1/2026.

With the widespread use of vaccines in research and clinical settings, there is an urgent need to standardize vaccine representation, integrate information across diverse vaccine types, and support computer-assisted reasoning. Accordingly, we have since 2007 developed the community-based Vaccine Ontology (VO), which aligns with the Basic Formal Ontology and adheres to OBO Foundry principles. VO models ontologically vaccines, vaccine components, vaccine immune responses, vaccine investigation studies and other vaccine-related topics. VO represents more than 10,000 vaccines targeting 289 infectious pathogens and cancers in humans and over 30 nonhuman animal species. VO provides mappings to external resources such as RxNorm, CVX, FDA, and USDA. Various VO use cases exist. VO facilitates vaccine standardization in resources such as the VIOLIN vaccine database, ImmPort, and the Vaccine Adjuvant Compendium (VAC). Semantic queries can be made to query VO. VO has been shown to enhance experimental and clinical vaccine data analysis and vaccine literature mining. Overall, VO standardizes vaccine modeling and representation and greatly supports vaccine AI research in the Semantic Web era.

Accurately mapping legal terminology across languages remains a significant challenge, especially for language pairs like Chinese and Japanese, which share a large number of homographs with different meanings. Existing resources and standardized tools for these languages are limited. To address this, we propose a human-AI collaborative approach for building a multilingual legal terminology database, based on a multi-agent framework. This approach integrates advanced large language models (LLMs) and legal domain experts throughout the entire process—from raw document preprocessing, article-level alignment, to terminology extraction, mapping, and quality assurance. Unlike a single automated pipeline, our approach places greater emphasis on how human experts participate in this multi-agent system. Humans and AI agents take on different roles: AI agents handle specific, repetitive tasks, such as OCR, text segmentation, semantic alignment, and initial terminology extraction, while human experts provide crucial oversight, review, and supervise the outputs with contextual knowledge and legal judgment. We tested the effectiveness of this framework using a trilingual parallel corpus comprising 35 key Chinese statutes, along with their English and Japanese translations. The experimental results show that this human-in-the-loop, multi-agent workflow not only improves the precision and consistency of multilingual legal terminology mapping but also offers greater scalability compared to traditional manual methods. Additionally, we observed that several open-source large language models performed exceptionally well in legal terminology extraction, demonstrating their cost-effectiveness and potential for sustainable applications in multilingual legal natural language processing (NLP). Finally, the open, extensible platform we developed supports continuous expert curation and can be easily integrated into various legal translation, research, and AI-powered knowledge management tools.

Language comprehension involves simulating event representations. However, previous research has primarily focused on discrete linguistic cues, paying little attention to how syntactic constructions influence experiential simulations. This study examines Mandarin Chinese ditransitive sentences that imply either of two transfer directions of entities: “giving” (transfer from the subject to the indirect object) and “receiving” (transfer from the indirect object to the subject). We engaged native Chinese participants in saccadic tasks in which they read ditransitive or static existential prime sentences (the preceding sentence), and then performed a target word (the following word) identification task. Experiments 1 and 2 investigated whether entity transfers in different directions are simulated. Results showed that participants responded faster when the transfer direction of the ditransitive prime sentences matched the location of the target object nouns, whereas no such difference was observed after static existential prime sentences. Experiment 3 replicated this pattern using pseudo-verb ditransitive constructions, indicating that simulation effects operate beyond specific verb semantics. These findings suggest that ditransitive constructions systematically trigger mental simulations with spatial specificity, activating implicit directional processing that facilitates identification processes for spatially congruent targets. Our study sheds light on how constructional meanings learned through usage activate embodied cognition in language comprehension.