Despite the recent and ongoing progress in using text-mining tools to automatically analyze large text corpora, there remains significant potential to facilitate the study of social action in social science research. In this context, particularly the disambiguation (who is referred to in a text?) and specification (which demographic…

This paper presents WikiMorph, a tool that automatically breaks down words into morphemes, etymological compounds (morphemes from root languages), and generates contextual definitions for each component. It comes in two flavors: a dataset and a deep-learning-based model. The dataset was extracted from Wiktionary and contains over 450k entries. We…

For a QA system it's very important to have a notion of vocabulary used in questions and for building correct answers. Especially, when a word represents a concept, one can use related lexical instances to understand it and further extend the knowledge by using the associated information. In this work, we suggest a process of building a knowledge…

The Patch workshop explores creative/critical analyses that can map the collectively relevant topoi of semiosis in linguistic texts according to the three ecologies as articulated by Félix Guattari. As creative pedagogues both in service and critical of creative economics, we valourize a generative practice, one that results in successive creative…

This paper explores the concept of dynamically generating definitions using a deep-learning model. We do this by creating a dataset that contains definition entries and contexts associated with each definition. We then fine-tune a GPT-2 based model on the dataset to allow the model to generate contextual definitions. We evaluate our model with…

This study applies multimodal conversation analysis to examine how pupils of L2 English in Sweden make use of online translation tools (OTTs), i.e. bilingual dictionaries and Google Translate, in a range of digital collaborative writing tasks. The collection of sequences where pupils use OTTs comes from 31 hours of video-recorded data from four…

In the past two decades, the growing rage of computer mediated environments (CMC) affords new literacies and new opportunities for language learners to experience, construct, communicate, and access knowledge (Ware, Kern & Warschauer, 2016). Also, it suggests that writing in multimodal in the digital ear contributes to its production and…

Translation Studies MSc students at the University of Edinburgh take part in a Wikipedia translation assignment as part of their independent study component. The students make use of the free and open encyclopaedia's Content Translation tool which enables them to create translations side-by-side to the original article and automates the process of…

Aim/Purpose: Using Artificial Intelligence with Deep Learning (DL) techniques, which mimic the action of the brain, to improve a student's grammar learning process. Finding the subject of a sentence using DL, and learning, by way of this computer field, to analyze human learning processes and mistakes. In addition, showing Artificial Intelligence…

Automated Writing Evaluation (AWE) systems have been found to enhance the accuracy, readability, and cohesion of writing responses (Stevenson & Phakiti, 2019). Previous research indicates that individual learners may have difficulty utilizing content-based AWE feedback and collaborative processing of feedback might help to cope with this…

The increasingly widespread use of social software (e.g., Wikis, Google Docs) in second language (L2) settings has brought a renewed attention to collaborative writing. Although the current methodological approaches to examining collaborative writing are valuable to understand L2 students' interactional patterns or perceived experiences, they can…

Semantic distance is a determining factor in cognitive processes, such as semantic priming, operating upon semantic memory. The main computational approach to compute semantic distance is through latent semantic analysis (LSA). However, objections have been raised against this approach, mainly in its failure at predicting semantic priming. We…