The field of topic modeling has become increasingly important over the past few years. Topic modeling is an unsupervised machine learning way to organize text (or image or DNA, etc.) information such that related pieces of text can be identified. This paper/session will present/discuss the current state of topic modeling, why it is important, and…

This paper reports on the development of a prototype tool which shows how learners can be helped to reflect upon the accuracy of their writing. Analysis of samples of freely written texts by intermediate and advanced learners of English as a foreign language (EFL) showed evidence of weakness in the use of tense and aspect. Computational discourse…

Many excellent corpus-based language learning resources (e.g., concordancers) have been freely available on the Internet for some time. Google assisted language learning (GALL) is also gaining increasing acceptance. These tools are a potential resource for English as an additional language (EAL) university students who want to independently…

Maintains that the study of signs is divided between those scholars who use the Saussurian binary sign (semiology) and those who prefer the Peirce tripartite sign (semiotics). Concludes that neither the Saussurian nor Peircian analysis methods can produce a semiotic interpretation based on a hierarchy of the text's various components. (CFR)

This paper discusses the use of a web-based concordancing program using an interface design similar to the one used at the MICASE concordancing site to help students appropriately choose reporting verbs. Appropriate reporting verbs are important for asserting credible claims in academic papers. An interface was created that asked the students to…

Argues that psycholinguistics relies on a number of methodologies that bear little relation to actual language comprehension. Maintains that computer software illustrating classic experiments in psycholinguistics can introduce students to these techniques. The software examines experiments concerning reaction time, reading time, and recognition.…

This paper makes connections between the research reported in this issue the broader area of second language studies focusing on learner language, interaction, individual differences, linguistic analysis, and language learning and teaching. Theoretical, empirical and ethical challenges posed by technology-based second language studies are…

Considers problems of quantifying literary style. Examines several variables that may be used as stylistic "fingerprints" of a writer. Reviews work done on statistical analysis of change over time in literary style and applies this technique to the Bible. (CFR)

Speech technology--especially automatic speech recognition--has now advanced to a level where it can be of great benefit both to able-bodied people and those with various disabilities. In this paper we describe an application "TalkMaths" which, using the output from a commonly-used conventional automatic speech recognition system,…

Illustrates how Radial Basis Function (RBF) network techniques can be used to explore questions concerning authorship of historic documents. Demonstrates the utility and potential for using quantitative techniques to assist in the decision-making process in relatively subjective disciplines. Compares RBF neural network techniques with more…

Discusses the use of an instructional morphological parser (IMP) in the teaching of courses in theoretical and computational morphology. Provides an overview of computational morphology. Outlines the two courses and speculates on computational and linguistic concepts that students learned. Examines problems encountered in teaching about recursion.…

Describes the use of the California Central Coast Online Dictionary, a database-supported Web site, in teaching an introductory class on linguistics and lexicography. The project allowed consideration of several models for teaching in the information age: teaching as modeling, teaching as negotiation, and teaching as defamiliarization or…

Compares the success of lexical statistics, content analysis, and function words in determining the true author of "The Federalist." The function word approach proved most successful in attributing the papers to James Madison. Lexical statistics contributed nothing, while content analytic measures resulted in some success. (MJP)

Describes how linguistic analysis can change the computer from a generator of data that can be used to develop a critical analysis to a tool that provides a means to explore the processes and inputs that generate different interpretations of literary works. Illustrates this concept by analyzing a Shakespearean sonnet. (CFR)

Discusses "Minds and Machines," a one-semester undergraduate course for nontechnical majors. Explains that the course examines how philosophical problems of knowledge, cognition, language, and human nature can be investigated with computer-related concepts and techniques. Describes experiments conducted during the course, including mind…