# Intelligent Assistant Language Understanding On Device

arXiv: https://arxiv.org/abs/2308.03905 · HTML: https://mlsanity.com/paper/2308.03905/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 7 Aug 2023.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [MAttNet: Modular Attention Network for Referring Expression Comprehension](https://mlsanity.com/paper/1801.08186/) (2018)
- [Linguistic Knowledge and Transferability of Contextual Representations](https://mlsanity.com/paper/1903.08855/) (2019)
- [A Network-based End-to-End Trainable Task-oriented Dialogue System](https://mlsanity.com/paper/1604.04562/) (2016)
- [Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1905.08743/) (2019)
- [Neural Belief Tracker: Data-Driven Dialogue State Tracking](https://mlsanity.com/paper/1606.03777/) (2016)
- [Semantic Parsing for Task Oriented Dialog using Hierarchical Representations](https://mlsanity.com/paper/1810.07942/) (2018)
- [Conversational Semantic Parsing for Dialog State Tracking](https://mlsanity.com/paper/2010.12770/) (2020)
- [Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation](https://mlsanity.com/paper/1909.00754/) (2019)
- [Scaling Multi-Domain Dialogue State Tracking via Query Reformulation](https://mlsanity.com/paper/1903.05164/) (2019)
- [Multi-domain Dialog State Tracking using Recurrent Neural Networks](https://mlsanity.com/paper/1506.07190/) (2015)
- [CREAD: Combined Resolution of Ellipses and Anaphora in Dialogues](https://mlsanity.com/paper/2105.09914/) (2021)
- [Context Dependent Semantic Parsing: A Survey](https://mlsanity.com/paper/2011.00797/) (2020)
- [Lexicon-injected Semantic Parsing for Task-Oriented Dialog](https://mlsanity.com/paper/2211.14508/) (2022)

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

- [STEER: Semantic Turn Extension-Expansion Recognition for Voice Assistants](https://mlsanity.com/paper/2310.16990/) (2023)
- [UnionSparse: An Index-Efficient Sparsity Framework for Low-Bit Sparse LLM Inference on Edge](https://mlsanity.com/paper/2608.09291/) (2026)
- [EStream: Fast and Memory-Efficient MoE Prefill through Expert Virtualization on Mobile NPUs](https://mlsanity.com/paper/2609.06551/) (2026)

## Abstract (arXiv)

It has recently become feasible to run personal digital assistants on phones and other personal devices. In this paper we describe a design for a natural language understanding system that runs on device. In comparison to a server-based assistant, this system is more private, more reliable, faster, more expressive, and more accurate. We describe what led to key choices about architecture and technologies. For example, some approaches in the dialog systems literature are difficult to maintain over time in a deployment setting. We hope that sharing learnings from our practical experiences may help inform future work in the research community.