TUTORING: Instruction-Grounded Conversational Agent for Language Learners
نویسندگان
چکیده
In this paper, we propose Tutoring bot, a generative chatbot trained on large scale of tutor-student conversations for English-language learning. To mimic human tutor's behavior in language education, the tutor bot leverages diverse educational instructions and grounds to each instruction as additional input context response generation. As single generally involves multiple dialogue turns give student sufficient speaking practice, is required monitor capture when current should be kept or switched next instruction. For that, learned not only generate responses but also infer its teaching action progress conversation simultaneously by multi-task learning scheme. Our deployed under non-commercial use license at https://tutoringai.com.
منابع مشابه
Learning Grounded Language through Situated Interactive Instruction
We present an approach for learning grounded language from mixed-initiative human-robot interaction. Prior work on learning from human instruction has concentrated on acquisition of task-execution knowledge from domainspecific language. In this work, we demonstrate acquisition of linguistic, semantic, perceptual, and procedural knowledge from mixed-initiative, natural language dialog. Our appro...
متن کاملA multilingual embodied conversational agent for tutoring speech and language learning
Speech and language science and technology evolved under the assumption that speech was a solely auditory event. However, a burgeoning record of research findings reveals that our perception and understanding are influenced by a speaker's face and accompanying gestures, as well as the actual sound of the speech. Perceivers expertly use these multiple sources of information to identify and inter...
متن کاملAdaptive Tutoring in an Intelligent Conversational Agent System
This paper describes an adaptive online conversational intelligent tutoring system (CITS) called Oscar that delivers a personalised natural language tutorial. During the tutoring conversation, Oscar CITS dynamically predicts and adapts to a student’s learning style. Oscar CITS aims to mimic a human tutor by using knowledge of learning styles to adapt its tutoring style and improve the effective...
متن کاملEmbodied Conversational Agent to Motivate Learners towards Communication in English
Willingness to communicate (WTC) in a second language (L2) is believed to have a direct and sustained influence on learners’ actual usage frequency of the targeted language. To help overcome the lack of suitable environments to increase L2 learners’ WTC, our approach is to implement a WTC model based conversational agent. In this paper, we focus on the dialogue management aspects of our approac...
متن کاملEffective instruction for English learners.
The fastest-growing student population in U.S. schools today is children of immigrants, half of whom do not speak English fluently and are thus labeled English learners. Although the federal government requires school districts to provide services to English learners, it offers states no policies to follow in identifying, assessing, placing, or instructing them. Margarita Calderón, Robert Slavi...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the ... AAAI Conference on Artificial Intelligence
سال: 2023
ISSN: ['2159-5399', '2374-3468']
DOI: https://doi.org/10.1609/aaai.v37i13.27063