One of the challenges of learning Japanese as a Second Language (JSL) is finding the appropriate word for a particular usage. To address this challenge, we developed a collocational aid designed to suggest more appropriate collocations in Japanese. In particular, we address the problem of generating and ranking noun and verb candidates for…

This article discusses the development and functionalities of an intelligent computer-assisted language learning (ICALL) system. By way of example, we describe "E-Tutor", an ICALL system for L2 learners of German that has been in use for a decade. Based on advancements in technology, user studies with L2 learners of German as well as feedback…

This paper presents a "didactic triangulation" strategy to cope with the problem of reliability of NLP applications for computer-assisted language learning (CALL) systems. It is based on the implementation of basic but well mastered NLP techniques and puts the emphasis on an adapted gearing between computable linguistic clues and didactic features…

This paper presents a new version of Robo-Sensei's NLP (Natural Language Processing) system which updates the version currently available as the software package "ROBO-SENSEI: Personal Japanese Tutor" (Nagata, 2004). Robo-Sensei's NLP system includes a lexicon, a morphological generator, a word segmentor, a morphological parser, a syntactic…

In this paper we present a system for automatic correction of errors made by learners of English. The system has two novel aspects. First, machine-learned classifiers trained on large amounts of native data and a very large language model are combined to optimize the precision of suggested corrections. Second, the user can access real-life web…

In this article, we present an approach to the automatic correction of preposition errors in L2 English. Our system, based on a maximum entropy classifier, achieves average precision of 42% and recall of 35% on this task. The discussion of results obtained on correct and incorrect data aims to establish what characteristics of L2 writing prove…

Four grammar checkers, all of French Canadian origin, were evaluated: "Le Correcteur 101,""GramR,""Hugo Plus," and "French Proofing Tools." Results indicate that "Le Correcteur 101" is the best French grammar checker on the market and worth its premium cost. (two references) (CK)

Describes the three-tiered error annotation system designed to annotate the "French Interlanguage Database" (FRIDA) corpus. The research took place within a project that aims to produce a learner corpus-informed computer assisted language learning (CALL) program for French as a foreign language. (Author/VWL)

The strategy used in "Miniprof," a program designed to provide "intelligent" instruction on elementary topics in French, is described. At an erroneous response, the program engages the student in a Socratic dialog and uses three major functions: parsing, error diagnostics, and tutoring. (10 references) (Author/LB)

A convenient and user-friendly method for computer-based second-language instruction (especially exotic-alphabet languages) presents a "pool" of text chunks from which the student uses a mouse to select and drag the chunks to form answers. Several types of feedback, including edit markup, may be selected; revision consists of rearranging, adding,…

Discusses how computer-assisted language learning programs can generate error messages to help students in different ways. The article points out that an easier solution is to program a computer to recognize several different kinds of generic errors not related to any particular question but applicable to many situations, in order to generate…

Describes theoretical and practical considerations related to the provision of feedback in the written compositions of advanced foreign language learners of French. Discusses the approach taken to teaching and assessing writing skills of students and considers how using a computer-based composition annotation program can contribute to reduction of…

A computer grammar checker is described that evolved from a sample of errors and resulting in a taxonomy of 14 main and 93 subtypes. Using a 1,402-word stem electronic dictionary, an augmented transition network parser, and a set of disambiguating rules, the checker provides feedback for 7 types of errors. (12 references) (Author/LB)

Describes development and evaluation of an error analysis procedure for a computer-assisted language learning program using natural language processing techniques. The program can be used for learning passive voice in Japanese on any World Wide Web browser. The program enables learners to type sentences freely, detects errors, and displays…

Argues that when the principles of engineering are applied to development of computer-assisted language learning software, resulting products are more reliable, easier to maintain, and easier to modify later. Those principles were used in developing the Elementary Language Study Exerciser, a program that drills students and corrects their written…