VAL: Interactive Task Learning with GPT Dialog Parsing
Machine learning often requires millions of examples to produce static, black-box models. In contrast, interactive task learning (ITL) emphasizes incremental knowledge acquisition from limited instruction provided by humans in modalities such as natural language. However, ITL systems often suffer from brittle, error-prone language parsing, which limits their usability. Large language models (LLMs) are resistant to brittleness but are not interpretable and cannot learn incrementally. We present VAL, an ITL system with a new philosophy for LLM/symbolic integration. By using LLMs only for specific tasks--such as predicate and argument selection--within an algorithmic framework, VAL reaps the benefits of LLMs to support interactive learning of hierarchical task knowledge from natural language. Acquired knowledge is human interpretable and generalizes to support execution of novel tasks without additional training. We studied users' interactions with VAL in a video game setting, finding that most users could successfully teach VAL using language they felt was natural.
Code (0)
등록된 구현이 없습니다.
Tasks
PhilosophySimilar Papers 제목 키워드 기반
Towards Transparent Interactive Semantic Parsing via Step-by-Step Correction
Existing studies on semantic parsing focus primarily on mapping a natural-language utterance to a corresponding logical form in one turn. However, because natural language can contain a great deal of ambiguity and variab…
Question AnsweringSemantic ParsingUsnea: An Authorship Tool for Interactive Fiction using Retrieval Based Semantic Parsing
The reader of a choose your own adventure novel and the user of a modern virtual assistant have a subtle similarity; both may, through the right lens, be viewed as engaging with a work of Interactive Fiction. This litera…
RetrievalSemantic ParsingInteractive Semantic Parsing for If-Then Recipes via Hierarchical Reinforcement Learning
Given a text description, most existing semantic parsers synthesize a program in one shot. However, it is quite challenging to produce a correct program solely based on the description, which in reality is often ambiguou…
Hierarchical Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1Towards Transparent Interactive Semantic Parsing via Step-by-Step Correction
Existing studies on semantic parsing focus on mapping a natural-language utterance to a logical form (LF) in one turn. However, because natural language may contain ambiguity and variability, this is a difficult challeng…
Question AnsweringSemantic ParsingIntegrated Learning of Dialog Strategies and Semantic Parsing
Natural language understanding and dialog management are two integral components of interactive dialog systems. Previous research has used machine learning techniques to individually optimize these components, with diffe…
BIG-bench Machine LearningManagementNatural Language Understandingreinforcement-learning+3