Intelligent Language Tutoring System Research Articles

Integrating an Intelligent Language Tutoring System in Teaching English Grammar

This paper describes a research project using an intelligent language tutoring system model in teaching grammar in English. The study aims to investigate the perceptions of a group of students regarding the effectiveness of this system and its service quality. This investigation is significant since it gives further insights into how Intelligent Language Tutoring Systems can help students learn grammar in a personalized manner based on their levels. Research has revealed that classroom teaching may fall short in providing customized instruction and feedback. Therefore, intelligent language tutoring systems can support adaptivity to individual learner needs. In order to assess the effectiveness of this system, the participants answered a survey questionnaire at the end of this study. The research project involves a class of adult mixed-ability students in a continuing education program at the National School of Applied Sciences in Fes, Morocco. The results demonstrate that these students have a positive attitude toward the merits of such technological tools. These advantages are mainly related to enhancing learner achievement and motivation. Based on these findings, some implications for both teaching and learning grammar can be drawn.

Cyclic feeding interactions between finite-state mal-rules

Intelligent Language Tutoring Systems typically attempt to automatically diagnose learner errors in order to provide individualized feedback. One common approach is the use of mal-rules to extend normative grammars by licensing specific types of learner errors. In finite-state morphologies, mal-rules can be implemented as two-level rules or replace rules. However, unlike the phonological rules of natural languages, mal-rules do not necessarily behave as a coherent system, especially with respect to feeding interactions. Using examples from learner errors attested in the RULEC corpus of Russian learner texts, we illustrate the problem of cyclic feeding interactions that can occur between mal-rules. We then describe a formal algorithm for identifying an optimal ordering for mal-rules to be applied to a transducer.

Intelligent Language Tutoring System

Intelligent computer-assisted language learning (ICALL) is a multidisciplinary area of research that combines natural language processing (NLP), intelligent tutoring system (ITS), second language acquisition (SLA), and foreign language teaching and learning (FLTL). Intelligent tutoring systems (ITS) are able to provide a personalized approach to learning by assuming the role of a real teacher/expert who adapts and steers the learning process according to the specific needs of each learner. This article reviews and discusses the issues surrounding the development and use of ITSs for language learning and teaching. First, the authors look at ICALL history: its evolution from CALL. Second, issues in ICALL research and integration will be discussed. Third, they will explain how artificial intelligence (AI) techniques are being implemented in language education as ITS and intelligent language tutoring systems (ITLS). Finally, the successful integration and development of ITLS will be explained in detail.

Predicting the Difficulty of Exercise Items for Dynamic Difficulty Adaptation in Adaptive Language Tutoring

Advances in computer technology and artificial intelligence create opportunities for developing adaptive language learning technologies which are sensitive to individual learner characteristics. This paper focuses on one form of adaptivity in which the difficulty of learning content is dynamically adjusted to the learner’s evolving language ability. A pilot study is presented which aims to advance the (semi-)automatic difficulty scoring of grammar exercise items to be used in dynamic difficulty adaptation in an intelligent language tutoring system for practicing English tenses. In it, methods from item response theory and machine learning are combined with linguistic item analysis in order to calibrate the difficulty of an initial exercise pool of cued gap-filling items (CGFIs) and isolate CGFI features predictive of item difficulty. Multiple item features at the gap, context and CGFI levels are tested and relevant predictors are identified at all three levels. Our pilot regression models reach encouraging prediction accuracy levels which could, pending additional validation, enable the dynamic selection of newly generated items ranging from moderately easy to moderately difficult. The paper highlights further applications of the proposed methodology in the area of adapting language tutoring, item design and second language acquisition, and sketches out issues for future research.

Web Delivery of Adaptive and Interactive Language Tutoring: Revisited

This commentary reconsiders the description and assessment of the design and implementation of German Tutor, an Intelligent Language Tutoring System (ILTS) for learners of German as a foreign language, published in 2001. Based on our experience over the past 15 years with the design and real classroom use of an ILTS, we address a number of technological and pedagogical issues as they relate to the approach and motivation of designing an ILTS. We also discuss some of the core limitations of German Tutor that eventually resulted in E-Tutor, a modified and enhanced ILTS implemented in 2003 and further expanded in 2009. The commentary concludes with a description of the core contributions of German Tutor as a learner-centered ILTS. Since its initial implementation in 1998, German Tutor has been studied as a component of regular classroom instruction and this body of research has informed not only system upgrades and development but also studies of learner-computer interactions or, computer-assisted language learning (CALL), more generally.

Analysis and feedback of erroneous Arabic verbs

AbstractArabic language is strongly structured and considered as one of the most highly inflected and derivational languages. Learning Arabic morphology is a basic step for language learners to develop language skills such as listening, speaking, reading, and writing. Arabic morphology is non-concatenative and provides the ability to attach a large number of affixes to each root or stem that makes combinatorial increment of possible inflected words. As such, Arabic lexical (morphological and phonological) rules may be confusing for second language learners. Our study indicates that research and development endeavors on spelling, and checking of grammatical errors does not provide adequate interpretations to second language learners’ errors. In this paper we address issues related to error diagnosis and feedback for second language learners of Arabic verbs and how they impact the development of a web-based intelligent language tutoring system. The major aim is to develop an Arabic intelligent language tutoring system that solves these issues and helps second language learners to improve their linguistic knowledge. Learners are encouraged to produce input freely in various situations and contexts, and are guided to recognize by themselves the erroneous functions of their misused expressions. Moreover, we proposed a framework that allows for the individualization of the learning process and provides the intelligent feedback that conforms to the learner's expertise for each class of error. Error diagnosis is not possible with current Arabic morphological analyzers. So constraint relaxation and edit distance techniques are successfully employed to provide error-specific diagnosis and adaptive feedback to learners. We demonstrated the capabilities of these techniques in diagnosing errors related to Arabic weak verbs formed using complex morphological rules. As a proof of concept, we have implemented the components that diagnose learner's errors and generate feedback which have been effectively evaluated against test data acquired from real teaching environment. The experimental results were satisfactory, and the performance achieved was 74.34 percent in terms of recall rate.

Learner Control and Error Correction in ICALL

This article reports the findings of a study on the impact of learner control on the error correction process within a web-based Intelligent Language Tutoring System (ILTS). During three one-hour grammar practice sessions, 33 students used an ILTS for German that provided error-specific and individualized feedback. In addition to receiving detailed error reports, students had the option of peeking at the correct answer, even before submitting a sentence (browsing). The results indicate that the majority of students (85%) sought to correct errors on their own most of the time, and that 18% of students abstained entirely from looking up answers. Furthermore, the results identify language skill as a predictor for students belonging to the group of Browsers, Frequent Peekers, Sporadic Peekers, and Adamants.

Bug Diagnosis By String Matching

We have developed an entirely new template-automaton-based knowledge database system for an interactive intelligent language tutoring system (ILTS) for Japanese-English translation whereby model translations as well as a taxonomy of bugs extracted from ill formed translations typical of nonnative learners are collected. Unlike conventional rule-based systems whose complicated solution search procedure and labor-intensive processing have led to so-called knowledge engineer bottlenecks of the expert systems, the new dynamic programming-based heaviest common sequence (HCS) matching algorithm is both efficient and robust in which error diagnosis is implemented by selecting, from among many candidates' paths in the system template, a path having an HCS of a highest similarity with a student's free-format translation input. This best matched path to the given ill formed sentence is used to provide contingent feedback messages. We have laid down a theoretical framework for the global HCS matching algorithm which is applied to the dual form of acyclic weighted digraphs by topologically sorting the template automaton structured according to augmented transition networks. An extensive evaluation test of the diagnostic engine has ensured the validity, efficiency, and robustness of the algorithm in providing error-contingent feedback to a wide spectrum of learners even with different educational backgrounds.

Student Model of Technical Japanese Reading Proficiency for an Intelligent Tutoring System

This article presents the development of a student model that is used in a Japanese language intelligent tutoring system to assess pupils' proficiency at reading technical Japanese. A computer-assisted knowledge acquisition system is designed to generate a domain knowledge base for a Japanese language intelligent tutoring system. The domain knowledge represents a model of the expertise that a native English speaker must acquire in order to be proficient at reading technical Japanese. The algorithms described here are able to generate a set of grammatical transformation rules that clarify changes of syntactic structures between a Japanese text and its corresponding English translation, use them to assess a student's proficiency, and then appropriately individualize the student's instructions.

Grammatical error diagnosis in fluid construction grammar: a case study in L2 Spanish verb morphology

Construction grammar (CG) has been proposed as an adequate grammatical formalism for building intelligent language tutoring systems because it is highly compatible with the learning strategies observed in second language learning. Unfortunately, the lack of computational CG implementations has made it impossible in the past to corroborate these proposals with actual language tutoring prototypes. However, recent advances in Fluid Construction Grammar (FCG) now offer exciting new ways of operationalizing robust and open-ended language processing within a CG approach. This paper demonstrates its adequacy for ICALL applications through a case study on error diagnosis in the domain of Spanish tense, aspect and modal morphology. The performance of the FCG tutor is tested on the Spanish Learner Language Oral Corpus (SPLOCC 2). This first FCG Spanish error diagnostic prototype achieves an accuracy of 70% on a total of 500 conjugation errors in four oral tasks carried out by 20 low intermediate and 20 advanced English learners of Spanish. Follow-up experiments will test this prototype on larger learner corpora of differing proficiency levels.

Analyzing learner language: towards a flexible natural language processing architecture for intelligent language tutors

Intelligent language tutoring systems (ILTS) typically analyze learner input to diagnose learner language properties and provide individualized feedback. Despite a long history of ILTS research, such systems are virtually absent from real-life foreign language teaching (FLT). Taking a step toward more closely linking ILTS research to real-life FLT, in this article we investigate the connection between FLT activity design and the system architecture of an ILT system. We argue that a demand-driven, annotation-based natural language processing (NLP) architecture is well-suited to handle the demands posed by the heterogeneous learner input which results when supporting a wider range of FLT activity types. We illustrate how the unstructured information management architecture (UIMA) can be used in an ILTS, thereby connecting the specific needs of activities in foreign language teaching to the current research and development of NLP architectures in general. Making the conceptual issues concrete, we discuss the design and realization of a UIMA-based reimplementation of the NLP in the TAGARELA system, an intelligent web-based tutoring system supporting the teaching and learning of Portuguese.

Integrating parallel analysis modules to evaluate the meaning of answers to reading comprehension questions

Contextualised, meaning-based interaction in the foreign language is widely recognised as crucial for second language acquisition. Correspondingly, current exercises in foreign language teaching generally require students to manipulate both form and meaning. For intelligent language tutoring systems to support such activities, they thus must be able to evaluate the appropriateness of the meaning of a learner response for a given exercise. We discuss such a content-assessment approach, focusing on reading comprehension exercises. We pursue the idea that a range of simultaneously available representations at different levels of complexity and linguistic abstraction provide a good empirical basis for content assessment. We show how an annotation-based NLP architecture implementing this idea can be realised and that it successfully performs on a corpus of authentic learner answers to reading comprehension questions. To support comparison and sustainable development on content assessment, we also define a general exchange format for such exercise data.

A natural language intelligent tutoring system for training pathologists: implementation and evaluation

We developed and evaluated a Natural Language Interface (NLI) for an Intelligent Tutoring System (ITS) in Diagnostic Pathology. The system teaches residents to examine pathologic slides and write accurate pathology reports while providing immediate feedback on errors they make in their slide review and diagnostic reports. Residents can ask for help at any point in the case, and will receive context-specific feedback. We evaluated (1) the performance of our natural language system, (2) the effect of the system on learning (3) the effect of feedback timing on learning gains and (4) the effect of ReportTutor on performance to self-assessment correlations. The study uses a crossover 2 x 2 factorial design. We recruited 20 subjects from 4 academic programs. Subjects were randomly assigned to one of the four conditions--two conditions for the immediate interface, and two for the delayed interface. An expert dermatopathologist created a reference standard and 2 board certified AP/CP pathology fellows manually coded the residents' assessment reports. Subjects were given the opportunity to self grade their performance and we used a survey to determine student response to both interfaces. Our results show a highly significant improvement in report writing after one tutoring session with 4-fold increase in the learning gains with both interfaces but no effect of feedback timing on performance gains. Residents who used the immediate feedback interface first experienced a feature learning gain that is correlated with the number of cases they viewed. There was no correlation between performance and self-assessment in either condition.

A Table Look-Up Parser in Online ILTS Applications

A simple table look-up parser (TLUP) has been developed for parsing and consequently diagnosing syntactic errors in semi-free formatted learners' input sentences of an intelligent language tutoring system (ILTS). The TLUP finds a parse tree for a correct version of an input sentence, diagnoses syntactic errors of the learner by tracing and regarding the deviations of the input from the identified correct sentences as errors of the learner. The TLUP can now display the parse tree as well as diagnosed errors at leaves' level. This simple super-rule based TLUP turns out to be a powerful pedagogic tool coaching L2 (second language) learners on the grammar structures in L2, saving the computing time and running space requirements, improving the parsing accuracy and allowing the real time online running environments to be applicable. The TLUP is effective as long as the input does not deviate too much from anticipated embedded patterns of model answers with committed errors remaining within the framework of anticipation for the level of the ITLS designed. We establish the validity of a TLUP by an (n, c) lot acceptance – sampling plan.

Student modeling and ab initio Language Learning

This paper provides examples of student modeling techniques that have been employed in computer-assisted language learning (CALL) over the past decade. We further discuss two of our own systems and show how different types of CALL programs can, nonetheless, share similar conceptual designs of a student model. First, we describe the German Tutor , an Intelligent Language Tutoring System (ILTS) for German as a Second Language which contains a parser and a grammar that analyze student input. The student model is based on student subject matter performance and provides feedback and remedial exercises suited to learner expertise. Second, we provide an overview of Geroline, an online distance education course for ab initio German learners, and its student model. We show how a student model can support computerized adaptive language testing for diagnostic purposes in a Web-based language learning environment which does not rely on parsing technology. Here, student scores from libraries of sentence-based exercises are used as the raw input for the model.

The Tutor Assistant: An Authoring Tool for an Intelligent Language Tutoring System

This paper describes the Tutor Assistant, an authoring tool for an Intelligent Language Tutoring systems (ILTS) for English as a Second Language (ESL). The common goal of authoring tools for ITSs is to reduce the costs in expertise and time that is required to produce a usable intelligent learning environment. The Tutor Assistant is designed to be usable by language instructions with little of no experience of ILTSs and ILTS authoring tools. This paper reports on a recent study which evaluates the degree to which typical users of our system can author good quality content for an ILTS and establishes benchmarks for development times.

A POST Parser-Based Learner Model for Template-Based ICALL for Japanese-English Writing Skills

Improving the parsing accuracy of a statistical ‘context sensitive’ parser, we have developed a new learner model which is capable of identifying the structural deficiencies of a learner for the template-automaton-based ICALL (intelligent language tutoring system) of Japanese-English writing skill (Tokuda & Chen, 2001). The parsing accuracy of corpus-based parsers is improved first by pre-assigning POS (part-of-speech) tags to well-formed sentences in a template and then by making use of a compound dictionary of idiomatic phrases. By defining the minimum unit of a parsed tree as a Minimum Error Sub-Tree if the unit contains an heaviest common sequence (HCS) -based static error(s) identified, we show how the new syntactic-based learner model can now be used to identify the structural deficiencies of a learner largely due to structural differences between his first and second languages, thus introducing an entirely new scheme of remediation in the ICALL system.

An online tutoring system for language translation

Our interactive intelligent language tutoring system acquires Japanese-English technical translations over the Internet. The system consists of an augmented transition network-based template, a global-matching algorithm embedded in the template structure, a parts-of-speech tagged parser, and a visual interface authoring tool. Acquiring key English patterns greatly simplifies the template structure, which effectively controls an exponential explosion in the number of possible combinations inherent in many natural language applications.

A RULE NETWORK FOR ENGLISH ARTICLE USAGE WITHIN AN INTELLIGENT LANGUAGE TUTORING SYSTEM

An Intelligent Language Tutoring System (ILTS) incorporates representations of the subject matter, the learner, and the tutoring process. Of these, it is understood that the most difficult to develop to any level of completeness is the system's knowledge of the subject matter, the domain model. Such knowledge can be used both in the prediction of grammaticality and in the detection and correction of learner errors. To develop a domain model of a language or an aspect of a language, it is necessary to formalise the native speaker's knowledge, in a way that is both representationally adequate and useful pedagogically, thus implying an interaction between formal and pedagogical grammar approaches. This paper describes the development of a domain model for English article usage, an area of the English language with which certain learners often have difficulties, which has been implemented within the ILTS ArtCheck.

An algorithm for domain knowledge base acquisition in an intelligent tutoring system: Japanese transliteration rules

This article describes an algorithm for developing a domain knowledge base that is used in a Japanese language intelligent tutoring system. The domain knowledge represents a model of the expertise that a student must acquire in order to be proficient at reading one of the distinct orthographies of Japanese, known as katakana. Whereas the effort required to memorize the relatively few katakana symbols and their associated pronunciations is not prohibitive, a major difficulty in reading katakana is associated with the phonetic modifications which occur when English words which are transliterated into katakana are made to conform to the more restrictive rules of Japanese phonology. The algorithm described here is able to generate a knowledge base of these phonological transformation rules automatically, that is subsequently used to assess a student's proficiency and then appropriately individualize the student's instruction.