Identifying word correspondence in parallel texts

Abstract

Researchers in both machine translation (e.g., Brown <i>et al</i>, 1990) and bilingual lexicography (e.g., Klavans and Tzoukermann, 1990) have recently become interested in studying <i>parallel texts</i> (also known as <i>bilingual corpora</i>), bodies of text such as the Canadian Hansards (parliamentary debates) which are available in multiple languages (such as French and English). Much of the current excitement surrounding parallel texts was initiated by Brown <i>et al.</i> (1990), who outline a self-organizing method for using these parallel texts to build a machine translation system.