Hybrid and Interactive Domain-Specific Translation for Multilingual Access to Digital Libraries

Abstract

Abstract. Accurate high-coverage translation is a vital component of reliable cross language information retrieval (CLIR) systems. This is particularly true for retrieval from archives such as Digital Libraries which are often specific to certain domains. While general machine translation (MT) has been shown to be effective for CLIR tasks in laboratory information retrieval evaluation tasks, it is generally not well suited to specialized situations where domain-specific translations are required. We demonstrate that effective query translation in the domain of cultural heritage (CH) can be achieved using a hybrid translation method which augments a standard MT system with domain-specific phrase dictionaries automatically mined from Wikipedia . We further describe the use of these components in a domain-specific interactive query translation service. The interactive system selects the hybrid translation by default, with other possible translations being offered to the user interactively to enable them to select alternative or additional translation(s). The objective of this interactive service is to provide user control of translation while maximising translation accuracy and minimizing the translation effort of the user. Experiments using our hybrid translation system with sample query logs from users of CH websites demonstrate a large improvement in the accuracy of domain-specific phrase detection and translation.

Information-seeking in multilingual digital libraries

“…In Wu and He’s (2012) study regarding Chinese–English information retrieval, their MT systems provided high-quality translations and were more robust in handling untranslated terms; these results, however, were not consistent with other studies that reported that the language structure or the domain-specific queries contributed to weaken the MT (Jones et al , 2011; Petrelli and Clough, 2012; Ture and Lin, 2014; Vassilakaki and Garoufallou, 2013). Wu and He (2012) reported that statistical MT has increased the effectiveness of the translations: “Statistical MT has become the state of the art for MT in many application areas, and even some commercial MT systems such as Google Translate (http://translate.google.com/translate) are statistical MT systems” (p. 432).…”