Grammar Control in Dialogue Response Generation for Language Learning Chatbots

• URL: http://arxiv.org/abs/2502.07544v1
• Date: Tue, 11 Feb 2025 13:30:41 GMT
• Title: Grammar Control in Dialogue Response Generation for Language Learning Chatbots
• Authors: Dominik Glandorf, Peng Cui, Detmar Meurers, Mrinmaya Sachan,
• Abstract summary: We control grammar in conversation practice by grounding a dialogue response generation model in a pedagogical repository of grammar skills. We evaluate prompting, fine-tuning, and decoding strategies for grammar-controlled dialogue response generation. Our simulation predicts grammar-controlled responses to support grammar acquisition adapted to learner proficiency.
• Score: 45.94196359404643
• License:
• Abstract: Chatbots based on large language models offer cheap conversation practice opportunities for language learners. However, they are hard to control for linguistic forms that correspond to learners' current needs, such as grammar. We control grammar in chatbot conversation practice by grounding a dialogue response generation model in a pedagogical repository of grammar skills. We also explore how this control helps learners to produce specific grammar. We comprehensively evaluate prompting, fine-tuning, and decoding strategies for grammar-controlled dialogue response generation. Strategically decoding Llama3 outperforms GPT-3.5 when tolerating minor response quality losses. Our simulation predicts grammar-controlled responses to support grammar acquisition adapted to learner proficiency. Existing language learning chatbots and research on second language acquisition benefit from these affordances. Code available on GitHub.

Related papers

• Measuring and Controlling Instruction (In)Stability in Language Model Dialogs [72.38330196290119]
  System-prompting is a tool for customizing language-model chatbots, enabling them to follow a specific instruction. We propose a benchmark to test the assumption, evaluating instruction stability via self-chats. We reveal a significant instruction drift within eight rounds of conversations. We propose a lightweight method called split-softmax, which compares favorably against two strong baselines.
  arXiv  Detail & Related papers  (2024-02-13T20:10:29Z)
• Curriculum-Driven Edubot: A Framework for Developing Language Learning Chatbots Through Synthesizing Conversational Data [23.168347070904318]
  We present Curriculum-Driven EduBot, a framework for developing a chatbots that combines the interactive features of chatbots with the systematic material of English textbooks. We begin by extracting pertinent topics from textbooks and using large language models to generate dialogues related to these topics.
  arXiv  Detail & Related papers  (2023-09-28T19:14:18Z)
• Developing Effective Educational Chatbots with ChatGPT prompts: Insights from Preliminary Tests in a Case Study on Social Media Literacy (with appendix) [43.55994393060723]
  Recent advances in language learning models with zero-shot learning capabilities, such as ChatGPT, suggest a new possibility for developing educational chatbots. We present a case study with a simple system that enables mixed-turn chatbots interactions. We examine ChatGPT's ability to pursue multiple interconnected learning objectives, adapt the educational activity to users' characteristics, such as culture, age, and level of education, and its ability to use diverse educational strategies and conversational styles.
  arXiv  Detail & Related papers  (2023-06-18T22:23:18Z)
• Controllable Mixed-Initiative Dialogue Generation through Prompting [50.03458333265885]
  Mixed-initiative dialogue tasks involve repeated exchanges of information and conversational control. Agents gain control by generating responses that follow particular dialogue intents or strategies, prescribed by a policy planner. Standard approach has been fine-tuning pre-trained language models to perform generation conditioned on these intents. We instead prompt large language models as a drop-in replacement to fine-tuning on conditional generation.
  arXiv  Detail & Related papers  (2023-05-06T23:11:25Z)
• User Adaptive Language Learning Chatbots with a Curriculum [55.63893493019025]
  We adapt lexically constrained decoding to a dialog system, which urges the dialog system to include curriculum-aligned words and phrases in its generated utterances. The evaluation result demonstrates that the dialog system with curriculum infusion improves students' understanding of target words and increases their interest in practicing English.
  arXiv  Detail & Related papers  (2023-04-11T20:41:41Z)
• Using Chatbots to Teach Languages [43.866863322607216]
  Our system can adapt to users' language proficiency on the fly. We provide automatic grammar error feedback to help users learn from their mistakes. Our next step is to make our system more adaptive to user profile information by using reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2022-07-31T07:01:35Z)
• Few-Shot Bot: Prompt-Based Learning for Dialogue Systems [58.27337673451943]
  Learning to converse using only a few examples is a great challenge in conversational AI. The current best conversational models are either good chit-chatters (e.g., BlenderBot) or goal-oriented systems (e.g., MinTL) We propose prompt-based few-shot learning which does not require gradient-based fine-tuning but instead uses a few examples as the only source of learning.
  arXiv  Detail & Related papers  (2021-10-15T14:36:45Z)
• Conversational agents for learning foreign languages -- a survey [0.0]
  Conversational practice, while crucial for all language learners, can be challenging to get enough of and very expensive. This paper provides an overview of the chatbots for learning languages, critically analyze existing approaches, and discuss the major challenges for future work.
  arXiv  Detail & Related papers  (2020-11-16T12:27:02Z)
• The design and implementation of Language Learning Chatbot with XAI using Ontology and Transfer Learning [0.0]
  We design three levels for systematically English learning, including phonetics level for speech recognition and pronunciation correction, semantic level for specific domain conversation, and simulation of free-style conversation in English. Our Language Learning agent integrated the mini-program in WeChat as front-end, and fine-tuned GPT-2 model of transfer learning as back-end to interpret the responses by ontology graph.
  arXiv  Detail & Related papers  (2020-09-29T13:11:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.