Paper: Does the Phonology of L1 Show Up in L2 Texts?

ACL ID P14-2138
Title Does the Phonology of L1 Show Up in L2 Texts?
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014

The relative frequencies of character bi- grams appear to contain much information for predicting the first language (L1) of the writer of a text in another language (L2). Tsur and Rappoport (2007) interpret this fact as evidence that word choice is dic- tated by the phonology of L1. In order to test their hypothesis, we design an algo- rithm to identify the most discriminative words and the corresponding character bi- grams, and perform two experiments to quantify their impact on the L1 identifica- tion task. The results strongly suggest an alternative explanation of the effectiveness of character bigrams in identifying the na- tive language of a writer.