DeepAI AI Chat
Log In Sign Up

Improving Top-K Decoding for Non-Autoregressive Semantic Parsing via Intent Conditioning

by   Geunseob Oh, et al.

Semantic parsing (SP) is a core component of modern virtual assistants like Google Assistant and Amazon Alexa. While sequence-to-sequence-based auto-regressive (AR) approaches are common for conversational semantic parsing, recent studies employ non-autoregressive (NAR) decoders and reduce inference latency while maintaining competitive parsing quality. However, a major drawback of NAR decoders is the difficulty of generating top-k (i.e., k-best) outputs with approaches such as beam search. To address this challenge, we propose a novel NAR semantic parser that introduces intent conditioning on the decoder. Inspired by the traditional intent and slot tagging parsers, we decouple the top-level intent prediction from the rest of a parse. As the top-level intent largely governs the syntax and semantics of a parse, the intent conditioning allows the model to better control beam search and improves the quality and diversity of top-k outputs. We introduce a hybrid teacher-forcing approach to avoid training and inference mismatch. We evaluate the proposed NAR on conversational SP datasets, TOP TOPv2. Like the existing NAR models, we maintain the O(1) decoding time complexity while generating more diverse outputs and improving the top-3 exact match (EM) by 2.4 points. In comparison with AR models, our model speeds up beam search inference by 6.7 times on CPU with competitive top-k EM.


Improving Fluency of Non-Autoregressive Machine Translation

Non-autoregressive (nAR) models for machine translation (MT) manifest su...

Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialog

Semantic parsing using sequence-to-sequence models allows parsing of dee...

SmBoP: Semi-autoregressive Bottom-up Semantic Parsing

The de-facto standard decoding method for semantic parsing in recent yea...

An EM Approach to Non-autoregressive Conditional Sequence Generation

Autoregressive (AR) models have been the dominating approach to conditio...

Knowledge Transfer and Distillation from Autoregressive to Non-Autoregressive Speech Recognition

Modern non-autoregressive (NAR) speech recognition systems aim to accele...

Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsing

An effective recipe for building seq2seq, non-autoregressive, task-orien...