语言学习聊天机器人对话响应生成中的语法控制
Grammar Control in Dialogue Response Generation for Language Learning Chatbots
AI总结：
针对语言学习聊天机器人难以控制语法等语言形式以匹配学习者需求的问题，该研究将对话响应生成模型基于语法技能教学知识库，评估相关策略，发现策略性解码Llama3在容忍轻微质量损失时优于GPT-3.5，模拟显示其能支持适配学习者熟练度的语法习得。
摘要：
基于大型语言模型的聊天机器人为语言学习者提供了廉价的对话练习机会。然而，它们难以控制与学习者当前需求对应的语言形式，例如语法。我们通过将对话响应生成模型基于语法技能的教学知识库来控制聊天机器人对话练习中的语法。我们还探索了这种控制如何帮助学习者生成特定语法。我们全面评估了语法控制对话响应生成的提示、微调和解码策略。在容忍轻微响应质量损失的情况下，对Llama3进行策略性解码优于GPT-3.5。我们的模拟预测语法控制的响应能支持适应学习者熟练度的语法习得。现有语言学习聊天机器人和第二语言习得研究将从这些功能中受益。代码可在GitHub上获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
