Reports

Permanent URI for this collectionhttps://hdl.handle.net/10125/49392

Browse

Now showing 1 - 14 of 14

Interview Buddy: Refining language skills through personalized, automated interviews
(Language Flagship Technology Innovation Center, University of Hawaii at Manoa, 2025-07-10) Gunkel, Lucas
This paper presents Interview Buddy, a custom GenAI-powered chatbot designed to emulate oral proficiency interview formats such as the Oral Proficiency Interview (OPI) and Peace Corps Language Proficiency Interview (PCLPI). Developed as part of a three-month hybrid internship, Interview Buddy seeks to address the resource and scalability challenges inherent in personalized verbal language assessments by providing an accessible, automated training tool. The system integrates uploaded knowledge repositories, JSON-based behavioral instructions, and a phased interview ap- proach incorporating climbing and spiraling ques- tion difficulty. Quality assurance testing across multiple languages revealed both the potential of the system and several key limitations, including memory constraints, hallucinated content, and sequencing errors. To address these challenges, the paper explores potential solutions such as models with larger context windows, external memory management through a Flask microserver, and integration with workflow automation tools like n8n. While there is considerable room for refinement, Interview Buddy represents a promising step toward scalable, technology-driven solutions for language proficiency assessment.
Exploring Brazilian Portuguese Meanings
(Language Flagship Technology Innovation Center, University of Hawaii at Manoa, 2025-07-09) Rivera, Arianna
This report outlines my internship experience where I focused on a vital resource for Portuguese Flagship students: an interactive chatbot that aids with word choice. My custom GPT facilitates learning about vocabulary nuance in a fun and interactive way trained on specialized linguistics data. The work described in this paper was supported through a Spring internship sponsored by the Language Flagship Technology Innovation Center at the University of Hawai‘i at Manoa. Faculty supervision of this work was provided by Dr. Rachel Mamiya Hernandez and Dr. Richard Medina.
Developing Human-AI authoring systems for the creation of study and practice materials
(Language Flagship Technology Innovation Center, 2024-08-20) Gerald, Scott Fitz
This internship was centered around the goal of developing a human-AI authoring system to facilitate the creation of study and practice materials. The main development involved with this project was associated with the creation of a software library that, when called, will prompt a generative AI to create questions of various formats related to the material provided. To accomplish this, the library is passed a text file with specific param- eters, like an integer to specify the number of questions that the user would like it to output. The end goal being to implement it into a pipeline that intakes an audio file and outputs these questions. Within the pipeline, the audio file is passed to an Automated Speech Recognition software. A transcript is produced which acts as the text file in the developed software library to create practice questions. To better visualize the output, an interactive web application was developed with Django. Output was also evaluated to rate the questions generated by the AI. Overall, output was judged to be acceptable for usage when paired with the review of an instructor.
Flagship Connect: Connecting through stories and games
(Language Flagship Technology Innovation Center, University of Hawaii at Manoa, 2024-08-20) Cheng, Michelle
This report outlines my internship experience, focusing on two main projects for the Flagship Connect Platform: the blog component of the Flagship Connect platform and an AI language learning game named Facade. The Flagship Connect Blog aims to provide a space for Language Flagship students and alumni to share experiences and knowledge with the entire community. Facade is a language learning game that leverages generative AI to help students improve their language proficiency in an engaging and enjoyable manner. The work described in this paper was supported through a Summer internship sponsored by the Language Flagship Technology Innovation Center at the University of Hawai‘i at Mānoa with additional support from the Center for Language & Technology. This report was submitted for review on August 8, 2024. Faculty supervision of this work was provided by Dr. Richard Medina.
Pathways Through Intercultural Communication
(Language Flagship Technology Innovation Center, University of Hawaii at Manoa, 2023-08-11) Jankoski, Chase
Guidebook on Prompting for Language Learning with ChatGPT
(Language Flagship Technology Innovation Center, University of Hawaii at Manoa, 2023-08-11) Nichols, Ashley
The purpose of this project was to create a guidebook on using ChatGPT for language learning. The intended audience of this guidebook is current students involved in The Language Flagship programs throughout the United States. Throughout the course of this project, it was found that current models of ChatGPT have difficulties in deciphering and correcting grammar mistakes, and that ChatGPT should be used in conjunction with classroom language studies where the student has regular access to a foreign language instructor.
Improving Speech-to-Text Transcription of Chinese Podcasts
(Language Flagship Technology Innovation Center, 2022-08) Schmitt, Elliot
The internship was spent contributing to the Tech Center’s ongoing podcast project; an ap- plication that will collect language podcasts and extract information from those podcasts that can help language learners and instructors better find relevant language learning materi- als. The podcast audio files are transcribed by software, and most of the work of the intern- ship was creating a markup tool that can im- prove the quality of the podcast transcriptions. The transcriptions were corrected by hand and then a rule-based approach was developed to correct errors the transcription software consis- tently made. This adds a layer of polish to the project, yielding cleaner and more accurate En- glish translations later on. The internship was largely exploratory, and the rest of the time was spent experimenting with other aspects of the project, such as researching lexical sophis- tication and how a metric for the sophistication of a text could be useful information to teach- ers or learners trying to gather useful study ma- terials.
VOT-CP: A Python Program for Automatic Data Codification and Calculation of Voice Onset Time
(Language Flagship Technology Innovation Center, 2021) Gutiérrez Topete, Ernesto
An Immersive Web Experience for Language Learning
(2021) Consolini, Carla
The Summarization of Arabic News Texts Using Probabilistic Topic Modeling for L2 Micro Learning Tasks
(2020-01-14) Elsayed, Issa
The field of Natural Language Processing (NLP) combines computer science, linguistic theory, and mathematics. Natural Language Processing applications aim at equipping computers with human linguistic knowledge. Applications such as Information Retrieval, Machine Translation, spelling checkers, as well as text sum- marization, are intriguing fields that exploit the techniques of NLP. Text summariza- tion represents an important NLP task that simplifies various reading tasks. These NLP-based text summarization tasks can be utilized for the benefits of language acquisition.
The Language Flagship Technology Innovation Center Blueprint for Success
(The Language Flagship Technology Innovation Center, 2019-10-05) The Language Flagship Technology Innovation Center
The Language Flagship Technology Innovation Center (Tech Center) at the University of Hawai‘i at Mānoa presents this Blueprint for Success in order to help The Language Flagship, as well as other federal initiatives and academic programs interested in enhancing high quality language programs, to improve language learning through the strategic integration of technology. Through multiple symposia and outreach events to promote input and collaboration across the Flagship programs, the Tech Center has worked to make the integration of effective language learning technology central to The Language Flagship mission. The participation and input of Language Flagship directors, instructors and students, along with colleagues from across academia, government and the private sector, has been instrumental in refining our views and practices in the integration of blended learning into high quality instruction. We offer these Goals and Guiding Principles to the Flagship Community to assist our efforts in the integration of best practices in technology-based learning into the overall programmatic approaches throughout academia and the federal and private sectors.
Stakeholder Views of the Place of Technology in Flagship Programs.
(The Language Flagship Technology Innovation Center, 2016) Brown, J. D.; Trace, J.; Rodriguez, Julio C.
Innovating Language Education: An NMC Horizon Project Strategic Brief
(2016) Adams Becker, Samantha; Rodriguez, Julio C.; Estrada, V.; Davis, A.
PERLS Pilot Study Report
(The Language Flagship Technology Innovation Center, 2017-08-30) Suvorov, Ruslan
The purpose of this pilot study was to investigate usability of the PERLS (PERvasive Learning System) app and its potential for micro-learning by exploring the nature of Flagship students’ engagement with it, identifying the strengths and weaknesses of its content and technological features, and determining how the app can promote and sustain language learning for both pre- and post-Capstone Flagship students. The pilot study took place during a 2-week period (July 17-August 1, 2017). Participants were 11 pre-Capstone and one post-Capstone Chinese Flagship students who participated in two 30-minute semi-structured interviews conducted at the end of the rst week (Round 1) and at the end of the second week of the pilot study (Round 2). Data obtained from 21 interviews (i.e., 12 interviews from Round 1 and nine interviews from Round 2) were summarily transcribed and qualitatively analyzed to identify emergent themes relevant to the purpose of the pilot study. Based on the analysis of the interview data, this report presents an executive summary of the main ndings and o ers recommendations for improving PERLS.

Browse

Recent Submissions