PurposeThe purpose of this paper is to address the knowledge acquisition bottleneck problem in natural language processing by introducing a new rule‐based approach for the automatic acquisition of linguistic knowledge.Design/methodology/approachThe author has developed a new machine translation methodology that only requires a bilingual lexicon and a parallel corpus of surface sentences aligned at the sentence level to learn new transfer rules.FindingsA first prototype of a web‐based Japanese‐English translation system called Japanese‐English translation using corpus‐based acquisition of transfer (JETCAT) has been implemented in SWI‐Prolog, and a Greasemonkey user script to analyze Japanese web pages and translate sentences via Ajax. In addition, linguistic information is displayed at the character, word, and sentence level to provide a useful tool for web‐based language learning. An important feature is customization; the user can simply correct translation results leading to an incremental update of the knowledge base.Research limitations/implicationsThis paper focuses on the technical aspects and user interface issues of JETCAT. The author is planning to use JETCAT in a classroom setting to gather first experiences and will then evaluate a real‐world deployment; also work has started on extending JETCAT to include collaborative features.Practical implicationsThe research has a high practical impact on academic language education. It also could have implications for the translation industry by superseding certain translation tasks and, on the other hand, adding value and quality to others.Originality/valueThe paper presents an extended version of the paper receiving the Emerald Web Information Systems Best Paper Award at iiWAS2010.