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

arXiv: https://arxiv.org/abs/2204.06748 · HTML: https://mlsanity.com/paper/2204.06748/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 35 references that are in the map.
- First posted on arXiv 14 Apr 2022.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement](https://mlsanity.com/paper/1802.06901/) (2018)
- [Better Fine-Tuning by Reducing Representational Collapse](https://mlsanity.com/paper/2008.03156/) (2020)
- [Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling](https://mlsanity.com/paper/1609.01454/) (2016)
- [Sequence-to-Sequence Learning as Beam-Search Optimization](https://mlsanity.com/paper/1606.02960/) (2016)
- [Insertion Transformer: Flexible Sequence Generation via Insertion Operations](https://mlsanity.com/paper/1902.03249/) (2019)
- [Semantic Parsing for Task Oriented Dialog using Hierarchical Representations](https://mlsanity.com/paper/1810.07942/) (2018)
- [Non-Autoregressive Machine Translation with Latent Alignments](https://mlsanity.com/paper/2004.07437/) (2020)
- [End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification](https://mlsanity.com/paper/1811.04719/) (2018)
- [Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing](https://mlsanity.com/paper/2010.03546/) (2020)
- [Imputer: Sequence Modelling via Imputation and Dynamic Programming](https://mlsanity.com/paper/2002.08926/) (2020)
- [Don't Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsing](https://mlsanity.com/paper/2001.11458/) (2020)
- [DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text](https://mlsanity.com/paper/1802.01345/) (2018)
- [Conversational Semantic Parsing](https://mlsanity.com/paper/2009.13655/) (2020)
- [Semi-Autoregressive Training Improves Mask-Predict Decoding](https://mlsanity.com/paper/2001.08785/) (2020)
- [Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsing](https://mlsanity.com/paper/2104.07275/) (2021)
- [Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialog](https://mlsanity.com/paper/2104.04923/) (2021)
- [Don't Parse, Insert: Multilingual Semantic Parsing with Insertion Based Decoding](https://mlsanity.com/paper/2010.03714/) (2020)
- [Compressing Transformer-Based Semantic Parsing Models using Compositional Code Embeddings](https://mlsanity.com/paper/2010.05002/) (2020)

## Built on by (most cited first, 3 of 3)

- [Shift-Reduce Task-Oriented Semantic Parsing with Stack-Transformers](https://mlsanity.com/paper/2210.11984/) (2022)
- [Step-Tagging: Toward controlling the generation of Language Reasoning Models through step monitoring](https://mlsanity.com/paper/2512.14332/) (2025)
- [TRACES: Tagging Reasoning Steps for Adaptive Cost-Efficient Early-Stopping](https://mlsanity.com/paper/2604.21057/) (2026)

## Abstract (arXiv)

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.