Controllable Semantic Parsing via Retrieval Augmentation

Abstract

In practical applications of semantic parsing, we often want to rapidly change the behavior of the parser, such as enabling it to handle queries in a new domain, or changing its predictions on certain targeted queries. While we can introduce new training examples exhibiting the target behavior, a mechanism for enacting such behavior changes without expensive model re-training would be preferable. To this end, we propose ControllAble Semantic Parser via Exemplar Retrieval (CASPER). Given an input query, the parser retrieves related exemplars from a retrieval index, augments them to the query, and then applies a generative seq2seq model to produce an output parse. The exemplars act as a control mechanism over the generic generative model: by manipulating the retrieval index or how the augmented query is constructed, we can manipulate the behavior of the parser. On the MTOP dataset, in addition to achieving state-of-the-art on the standard setup, we show that CASPER can parse queries in a new domain, adapt the prediction toward the specified patterns, or adapt to new semantic schemas without having to further re-train the model.

EMNLP 2021

References in corpus (10)

• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• CTRL: A Conditional Transformer Language Model for Controllable Generation
• Few-shot classification in Named Entity Recognition Task
• What Makes Good In-Context Examples for GPT-$3$?
• Calibrate Before Use: Improving Few-Shot Performance of Language Models
• Neural Data Augmentation via Example Extrapolation
• Learning Sparse Prototypes for Text Generation
• FewJoint: A Few-shot Learning Benchmark for Joint Language Understanding
• Vector Projection Network for Few-shot Slot Tagging in Natural Language Understanding

Cited by in corpus (2)

• Retrieval-Enhanced Machine Learning
• Machine Reading Comprehension using Case-based Reasoning