Learning to Learn Semantic Parsers from Natural Language Supervision

Abstract

As humans, we often rely on language to learn language. For example, when corrected in a conversation, we may learn from that correction, over time improving our language fluency. Inspired by this observation, we propose a learning algorithm for training semantic parsers from supervision (feedback) expressed in natural language. Our algorithm learns a semantic parser from users' corrections such as "no, what I really meant was before his job, not after", by also simultaneously learning to parse this natural language feedback in order to leverage it as a form of supervision. Unlike supervision with gold-standard logical forms, our method does not require the user to be familiar with the underlying logical formalism, and unlike supervision from denotation, it does not require the user to know the correct answer to their query. This makes our learning algorithm naturally scalable in settings where existing conversational logs are available and can be leveraged as training data. We construct a novel dataset of natural language feedback in a conversational setting, and show that our method is effective at learning a semantic parser from such natural language supervision.

arXiv commentpublished at EMNLP 2018

References in corpus (7)

• A Survey on Multi-view Learning
• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• Towards Universal Paraphrastic Sentence Embeddings
• Compositional Semantic Parsing on Semi-Structured Tables
• Language Understanding for Text-based Games Using Deep Reinforcement Learning
• Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision
• Data Recombination for Neural Semantic Parsing