Background: The emergence of ChatGPT in the education literature represents a transformative phase in educational technology research, marked by a surge in publications driven by initial research interest in new topics and media hype. While these publications highlight ChatGPT's potential in education, concerns arise regarding their quality,…

This article introduces the CELI corpus, a new learner corpus of written Italian consisting of ca. 600,000 tokens, evenly distributed among CEFR (Common European Framework of Reference for Languages) proficiency levels B1, B2, C1 and C2. The collected texts derive from the language certification exams administered by the University for Foreigners…

Bag-of-words is a commonly used text representation method for many text classification applications. However, bag-of-words representation fails to consider the context of the text because it only examines text documents based on the presence of individual words and explores relationships between texts with similar word choices (Bengfort, 2018).…

The variety and complexity of potentially-related data resources available for querying--webpages, databases, data warehouses--has been growing ever more rapidly. There is a growing need to pose integrative queries "across" multiple such sources, exploiting foreign keys and other means of interlinking data to merge information from diverse…

Multilingual lexicons are needed in various applications, such as cross-lingual information retrieval, machine translation, and some others. Often, these applications suffer from the ambiguity of dictionary items, especially when an intermediate natural language is involved in the process of the dictionary construction, since this language adds…

Using macro and micro-structure analysis of large files of personal author names, this study developed retrieval techniques and algorithms to automatically correct and/or flag typographical errors in names, identify names in a database that are similar to a name entered by a user during a search, and measure similarities between names. It was…

Presents a model for the a priori analysis of natural language queries which uses an algorithm to transform the query into a logical pattern that is used to determine the answerability of the query. The results of testing by a prototype system implemented in PROLOG are discussed. (20 references) (CLB)

Provides a bibliography of articles and book reviews on machine translation, computational linguistics and information storage and retrieval. All items listed were published in "Babel" during the years: 1956, 1957, 1960, 1962, 1964, 1965, 1967, 1968, 1974, 1976, 1977, 1978, and 1979. (MES)

This is a report on the activities of the survey of spoken English at the University of Lund (Sweden), during the period 1975-81. The aim of the survey has been to make available in machine-readable form a corpus of material with its origin in speech. The corpus was built in conjunction with the survey of English usage project at the University of…

Introduces some algorithmic methods, for which no pre-editing is necessary, for automatically "lemmatising" raw text (changing raw text to an equivalent version in which all inflected words are artificially transformed to their dictionary look-up form). The results of a study of these methods, which used a German Text, are also given. (KM)

The final report on a project to develop a standard corpus of present-day Mandarin Chinese is presented. This corpus consists of words of running text of Chinese prose printed in the Republic of China during the calendar year 1968. The corpus, although originally planned to have a total of 500 samples of 2000 words each, has only 294 samples. Each…

Reviews developments in research on information storage and retrieval, question-answering and natural language interface online systems, and the processes of synthesis and interpretation in intelligent behavior. Problem formulation, information requests, and knowledge representation are discussed in relation to the design and use of retrieval…

A description of a retrospective document retrieval system is given in which equifrequent fragments are used as language elements for compression coding and retrieval. The critical parameters governing the system are identified, and restrictions imposed by the parameters on the selection of fragments are outlined. Changes necessary in the…

The information service performed by the Royal Institute of Technology handles requests from both university users and from industry. Fourteen data bases are currently used for SDI purposes. The system is of a general nature which permits inclusion of various data bases of completely different tape formats. Any combination of elements of a…

A relational data system (RDS) is one that has the capability not only to retrieve specific facts but also the ability to deduce facts that are implicit rather than explicit in the data base. The study investigated the application of RDS technology to intelligence data processing. RDS technology and the nature of intelligence data processing are…