Training Naturalized Semantic Parsers with Very Little Data

European Conference on Artificial Intelligence(2022)

引用 7|浏览28
暂无评分
摘要
Semantic parsing is an important NLP problem, particularly for voice assistants such as Alexa and Google Assistant. State-of-the-art (SOTA) semantic parsers are seq2seq architectures based on large language models that have been pretrained on vast amounts of text. To better leverage that pretraining, recent work has explored a reformulation of semantic parsing whereby the output sequences are themselves natural language sentences, but in a controlled fragment of natural language. This approach delivers strong results, particularly for few-shot semantic parsing, which is of key importance in practice and the focus of our paper. We push this line of work forward by introducing an automated methodology that delivers very significant additional improvements by utilizing modest amounts of unannotated data, which is typically easy to obtain. Our method is based on a novel synthesis of four techniques: joint training with auxiliary unsupervised tasks; constrained decoding; self-training; and paraphrasing. We show that this method delivers new SOTA few-shot performance on the Overnight dataset, particularly in very low-resource settings, and very compelling few-shot results on a new semantic parsing dataset.
更多
查看译文
关键词
Natural Language Processing: Dialogue and Interactive Systems,Machine Learning: Few-shot learning,Natural Language Processing: Tagging, Chunking, and Parsing,Natural Language Processing: Natural Language Semantics
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要