Automated Alignment and Extraction of Bilingual Domain Ontology for Cross-Language Domain-Specific Applications

Automated Alignment and Extraction of Bilingual Ontology for Cross-Language Domain-Specific Applications Jui-Feng Yeh, Chung-Hsien Wu, Ming-Jun Chen and Liang-Chih Yu Department of Computer Science and Information Engineering National Cheng Kung University, Tainan, Taiwan, R.O.C. {jfyeh, chwu, mjchen,lcyu}@csie.ncku.edu.tw Abstract In this paper we propose a novel approach for ontology alignment and domain ontology extraction from the existing knowledge bases, WordNet and HowNet. These two knowledge bases are aligned to construct a bilingual ontology based on the co- occurrence of the words in the sentence pairs of a parallel corpus. The bilingual ontology has the merit that it contains more structural and semantic information coverage from these two complementary knowledge bases. For domain- specific applications, the domain specific ontology is further extracted from the bilingual ontology by the island-driven algorithm and the domain-specific corpus. Finally, the domain-dependent terminologies and some axioms between domain terminologies are integrated into the ontology. For ontology evaluation, experiments were conducted by comparing the benchmark constructed by the ontology engineers or experts. The experimental results show that the proposed approach can extract an aligned bilingual domain-specific ontology. 1 Introduction In recent years, considerable progress has been invested in developing the conceptual bases for building technology that allows knowledge reuse and sharing. As information exchangeability and communication becomes increasingly global, multilingual lexical resources that can provide transnational services are becoming increasingly important. On the other hand, multi-lingual ontology is very important for natural language processing, such as machine translation (MT), web mining (Oyama et al. 2004) and cross language information retrieval (CLIR). Generally, a multi- lingual ontology maps the keyword set of one language to another language, or compute the co- occurrence of the words among languages. In addition, a key merit for multilingual ontology is that it can increase the relation and structural information coverage by aligning two or more language-dependent ontologies with different semantic features. Over the last few years, significant effort has been made to construct the ontology manually according to the domain expert’s knowledge. Manual ontology merging using conventional editing tools without intelligent support is difficult, labor intensive and error prone. Therefore, several systems and frameworks for supporting the knowledge engineer in the ontology merging task have recently been proposed (Noy and Musen 2000). To avoid the reiteration in ontology construction, the algorithm of ontology merging (UMLS http://umlsks.nlm.nih.gov/) (Langkilde and Knight 1998) and ontology alignment (Vossen and Peters 1997) (Weigard and Hoppenbrouwers 1998) (Asanoma 2001) were invested. The final ontology is a merged version of the original ontologies. The two original ontologies persist, with aligned links between them. Alignment usually is performed when the ontologies cover domains that are complementary to each other. In the past, domain ontology was usually constructed manually according to the knowledge or experience of the experts or ontology engineers. Recently, automatic and semi-automatic methods have been developed. OntoExtract (Fensel et al. 2002) (Missikoff et al. 2002) provided an ontology engineering chain to construct the domain ontology from WordNet and SemCor. Nowadays vast investment is made in ontology construction for domain …

Content truncated to 500 words