Crossing the Border Twice: Reimporting Prepositions to Alleviate L1-Specific Transfer Errors

We present a data-driven approach which exploits word alignment in a large parallel corpus with the objective of identifying those verband adjective-preposition combinations which are difficult for L2 language learners. This allows us, on the one hand, to provide language-specific ranked lists in order to help learners to focus on particularly challenging combinations given their native language (L1). On the other hand, we provide extensive statistics on such combinations with the objective of facilitating automatic error correction for preposition use in learner texts. We evaluate these lists, first manually, and secondly automatically by applying our statistics to an error-correction task. Posted at the Zurich Open Repository and Archive, University of Zurich ZORA URL: https://doi.org/10.5167/uzh-137099 Published Version Originally published at: Graën, Johannes; Schneider, Gerold (2017). Crossing the Border Twice: Reimporting Prepositions to Alleviate L1-Specific Transfer Errors. In: Joint 6th Workshop on NLP for Computer Assisted Language Learning and 2nd Workshop on NLP for Research on Language Acquisition, Gothenburg, 22 May 2017 22 May 2017, 18-26. Crossing the Border Twice: Reimporting Prepositions to Alleviate L1-Specific Transfer Errors Johannes Graën Institute of Computational Linguistics University of Zurich [email protected] Gerold Schneider Institute of Computational Linguistics University of Zurich [email protected]