MALT - a Multi-lingual Adaptive Language Tutor
نویسندگان
چکیده
We describe a “Multi-lingual Adaptive Language Tutor” (MALT) that uses natural language parsing and text generation to create various kinds of grammar exercises for learners of any language. These exercises can be restricted to specific topics by the instructor such as transformation of verb tenses. MALT generates novel exercises focusing on the specific difficulties of language learners as determined from their past mistakes, helping them overcome individual difficulties faster. We also present the first preliminary results from employing MALT in the foreign language classroom at Notre Dame.
منابع مشابه
HMM-based polyglot speech synthesis by speaker and language adaptive training
This paper describes a technique for speaker and language adaptive training (SLAT) for HMM-based polyglot speech synthesis and its evaluations on a multi-lingual speech corpus. The SLAT technique allows multi-speaker/multi-language adaptive training and synthesis to be performed. Experimental results show that the SLAT technique achieves better naturalness than both speaker-adaptively trained l...
متن کاملMulti-lingual phoneme recognition exploiting acoustic-phonetic similarities of sounds
The aim of this work is to exploit the acoustic-phonetic similarities between several languages. In recent work cross{ language HMM-based phoneme models have been used only for bootstrapping the language{dependent models and the multi{lingual approach has been investigated only on very small speech corpora. In this paper, we introduce a statistical distance measure to determine the similarities...
متن کاملCross-lingual adaptation with multi-task adaptive networks
Posterior-based or bottleneck features derived from neural networks trained on out-of-domain data may be successfully applied to improve speech recognition performance when data is scarce for the target domain or language. In this paper we combine this approach with the use of a hierarchical deep neural network (DNN) network structure – which we term a multi-level adaptive network (MLAN) – and ...
متن کاملWaterloo at NTCIR-3: Using Self-supervised Word Segmentation
In this paper, we describe the system we use in the NTCIR-3 CLIR (cross language IR) task. We participate the SLIR (single language IR) track. In our system, we use a self-supervised word-segmentation technique for Chinese information retrieval, which combines the advantages of traditional dictionary based approaches with character based approaches, while overcoming many of their shortcomings. ...
متن کاملSemi-automatic test generation for tandem learning
We introduce a Web-based CALL architecture that facilitates the construction of learner-customized multiple choice tests in a cross-lingual tandem language learning environment. Mistakes made by the learner are manually corrected and classified by his tandem partner, who acts as a tutor. If the learner has problems to identify and correct his mistakes, or if he likes to practice, he can generat...
متن کامل