GenieTutor: a computer assisted second-language learning system based on semantic and grammar correctness evaluations

Abstract

This paper introduces a Dialog-Based Computer-Assisted second-Language Learning (DB-CALL) system using semantic and grammar correctness evaluations and the results of its experiment. While the system dialogues with English learners about a given topic, it automatically evaluates the grammar and content properness of their English utterances, then gives corrective feedback on grammar and semantics. The system consists of a non-native optimized speech recognition module and a semantic/grammar correctness evaluation based tutoring module. The tutoring module decides to continue the dialogue or asks learners to try again by evaluating semantic correctness of their utterances, and also gives them turn-by-turn semantic and grammatical corrective feedback. The semantic correctness evaluation consists of a 2-classes classifier for the 'pass or try again' and a 6-classes classifier for semantic corrective feedback, using the domain knowledge and language model. The grammatical correctness is evaluated by a hybrid grammatical error correction system composed of four approaches: a rule-based, a machine learning-based, an n-gram based, and an edit distance based approach. In the experiments, in which 30 subjects in a real environment took part, we acknowledged that the 'pass or try again' evaluation has a success rate of 97.5%, the semantic feedback classification has a success rate of 87.8%, and the precision and recall for grammar error correction are 79.2% and 60.9%, respectively. ISBN13: 978-1-908416-28-5 (Paperback -Print on demand, black and white) Print on demand technology is a high-quality, innovative and ecological printing method; with which the book is never 'out of stock' or 'out of print'. ISBN13: 978-1-908416-29-2 (Ebook, PDF, colour) ISBN13: 978-1-908416-30-8 (Ebook, EPUB, colour) Legal deposit, Ireland:

Task graph based task-oriented dialogue system using dialogue map for second language learning

“…Our TDS consists of a Structured Support Vector Machine (SSVM) based NLU (Kwon, Lee, Kim, & Lee, 2015), task graph-based dialogue management, and a generation template based Natural Language Generation (NLG). First, SSVMbased NLU analyses the learner utterance and determines the intention using SSVM training data.…”

Automatic dialogue scoring for a second language learning system

“…Then, there are two task turns, two passed user utterances out of all five user utterances, then the user utterance pass ratio is 40% while the task turn pass ratio is 100%. If a user utterance passes, the task turn is performed by the semantic correctness module (Kwon et al, 2015a).…”

“…A DB-CALL system usually provides grammar correction feedback with a grammar checker, and discourse feedback via a semantic checker. We have developed GenieTutor (Kwon, Lee, Kim, & Lee, 2015a;Kwon et al, 2015b), which is a DB-CALL system for English learners in Korea. GenieTutor leads dialogues by asking questions on different topics according to given scenarios, language learners answer questions orally, and the system recognises the speech, evaluates if the answers are semantically proper for given questions, and checks grammatical errors and provides feedback (Lee, Kwon, Kim, & Lee, 2015).…”

Task-oriented spoken dialog system for second-language learning

“…Many methods from the field of natural language processing and dialog processing have been employed in CALL (Johnson & Valente, 2009;Kwon, Lee, Kim 2015; Wilske, 2015). The approaches engage the learner in a dialog and provide educational feedback, focusing on either form-based instruction or meaning-based instruction.…”

“…The approaches engage the learner in a dialog and provide educational feedback, focusing on either form-based instruction or meaning-based instruction. Focus-on-form approaches tend to allow for relatively constrained input to provide more explicit feedback of linguistic forms and formal correctness about the learner's utterance (Kwon et al, 2015), whereas focus-on-meaning approaches tend to allow the learner to freely speak for providing opportunities for communication in the real world, but provide the less informative feedback (Wilske, 2015).…”