Approaching Language Transfer through Text Classification

Explorations in the Detection-based Approach

Edited by Dr. Scott Jarvis, Scott A. Crossley

Publication date:

14 March 2012

Publisher

Multilingual Matters

Dimensions:

234x156mm
6x9"

ISBN-13: 9781847696984

Recent work has pointed to the need for a detection-based approach to transfer capable of discovering elusive crosslinguistic effects through the use of human judges and computer classifiers that can learn to predict learners’ language backgrounds based on their patterns of language use. This book addresses that need. It details the nature of the detection-based approach, discusses how this approach fits into the overall scope of transfer research, and discusses the few previous studies that have laid the groundwork for this approach. The core of the book consists of five empirical studies that use computer classifiers to detect the native-language affiliations of texts written by foreign language learners of English. The results highlight combinations of language features that are the most reliable predictors of learners’ language backgrounds.

1 Scott Jarvis: The Detection-Based Approach: An Overview

2 Scott Jarvis, Gabriela Castañeda-Jiménez and Rasmus Nielsen: Detecting L2 Writers’ L1s on the Basis of their Lexical Styles

3 Scott Jarvis and Magali Paquot: Exploring the Role of N-Grams in L1 Identification

4 Scott A. Crossley and Danielle S. McNamara: Detecting the First Language of Second Language Writers Using Automated Indices of Cohesion, Lexical Sophistication, Syntactic Complexity, and Conceptual Knowledge

5 Yves Bestgen, Sylviane Granger and Jennifer Thewissen: Error Patterns and Automatic L1 Identification

6 Scott Jarvis, Yves Bestgen, Scott A. Crossley, Sylviane Granger, Magali Paquot, Jennifer Thewissen and Danielle S. McNamara: The Comparative and Combined Contributions of N-grams, Coh-Metrix Indices, and Error Types in the L1 Classification of Learner Texts

7 Scott A. Crossley: Detection-Based Approaches: Methods, Theories and Applications

In this bold and pioneering interdisciplinary study, experts on SLA research, computational analysis and statistics collaborate to try to identify the L1 background of non-native writers. The result is a most impressive work which will take the field of crosslinguistic studies a long way forward. A MUST for all SLA researchers!