arXiv subjects

He Tan

Publications and source records attributed to He Tan.

3 recordsLinked to original sources

arXiv2026

From Prompt to Graph: Comparing LLM-Based Information Extraction Strategies in Domain-Specific Ontology Development

Ontologies are essential for structuring domain knowledge, improving accessibility, sharing, and reuse. However, traditional ontology construction relies on manual annotation and conventional natural language processing (NLP) techniques, making the process labour-intensive and costly, especially in specialised fields like casting manufacturing. The rise of Large Language Models (LLMs) offers new possibilities for automating knowledge extraction. This study investigates three LLM-based approaches, including pre-trained LLM-driven method, in-context learning (ICL) method and fine-tuning method to extract terms and relations from domain-specific texts using limited data. We compare their performances and use the best-performing method to build a casting ontology that validated by domian expert.

cs.AI↗

arXiv2024

CODE-ACCORD: A Corpus of building regulatory data for rule generation towards automatic compliance checking

Automatic Compliance Checking (ACC) within the Architecture, Engineering, and Construction (AEC) sector necessitates automating the interpretation of building regulations to achieve its full potential. Converting textual rules into machine-readable formats is challenging due to the complexities of natural language and the scarcity of resources for advanced Machine Learning (ML). Addressing these challenges, we introduce CODE-ACCORD, a dataset of 862 sentences from the building regulations of England and Finland. Only the self-contained sentences, which express complete rules without needing additional context, were considered as they are essential for ACC. Each sentence was manually annotated with entities and relations by a team of 12 annotators to facilitate machine-readable rule generation, followed by careful curation to ensure accuracy. The final dataset comprises 4,297 entities and 4,329 relations across various categories, serving as a robust ground truth. CODE-ACCORD supports a range of ML and Natural Language Processing (NLP) tasks, including text classification, entity recognition, and relation extraction. It enables applying recent trends, such as deep neural networks and large language models, to ACC.

cs.IR↗

arXiv2010

A study on the relation between linguistics-oriented and domain-specific semantics

In this paper we dealt with the comparison and linking between lexical resources with domain knowledge provided by ontologies. It is one of the issues for the combination of the Semantic Web Ontologies and Text Mining. We investigated the relations between the linguistics oriented and domain-specific semantics, by associating the GO biological process concepts to the FrameNet semantic frames. The result shows the gaps between the linguistics-oriented and domain-specific semantics on the classification of events and the grouping of target words. The result provides valuable information for the improvement of domain ontologies supporting for text mining systems. And also, it will result in benefits to language understanding technology.

cs.AI↗