# Context-Aware Abbreviation Expansion Using Large Language Models

arXiv: https://arxiv.org/abs/2205.03767 · HTML: https://mlsanity.com/paper/2205.03767/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 45 references that are in the map.
- First posted on arXiv 8 May 2022.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [The Second Conversational Intelligence Challenge (ConvAI2)](https://mlsanity.com/paper/1902.00098/) (2019)
- [Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset](https://mlsanity.com/paper/1909.05358/) (2019)
- [Gmail Smart Compose: Real-Time Assisted Writing](https://mlsanity.com/paper/1906.00080/) (2019)
- [Smart Reply: Automated Response Suggestion for Email](https://mlsanity.com/paper/1606.04870/) (2016)
- [Structured abbreviation expansion in context](https://mlsanity.com/paper/2110.01140/) (2021)

## Built on by (most cited first, 5 of 5)

- [The Design Space of Generative Models](https://mlsanity.com/paper/2304.10547/) (2023)
- [Exploring Robustness of Multilingual LLMs on Real-World Noisy Data](https://mlsanity.com/paper/2501.08322/) (2025)
- [Using Large Language Models to Accelerate Communication for Users with Severe Motor Impairments](https://mlsanity.com/paper/2312.01532/) (2023)
- [Aging Up AAC: An Introspection on Augmentative and Alternative Communication Applications for Autistic Adults](https://mlsanity.com/paper/2404.17730/) (2024)
- [Your voice is your voice: Supporting Self-expression through Speech Generation and LLMs in Augmented and Alternative Communication](https://mlsanity.com/paper/2503.17479/) (2025)

## Abstract (arXiv)

Motivated by the need for accelerating text entry in augmentative and alternative communication (AAC) for people with severe motor impairments, we propose a paradigm in which phrases are abbreviated aggressively as primarily word-initial letters. Our approach is to expand the abbreviations into full-phrase options by leveraging conversation context with the power of pretrained large language models (LLMs). Through zero-shot, few-shot, and fine-tuning experiments on four public conversation datasets, we show that for replies to the initial turn of a dialog, an LLM with 64B parameters is able to exactly expand over 70% of phrases with abbreviation length up to 10, leading to an effective keystroke saving rate of up to about 77% on these exact expansions. Including a small amount of context in the form of a single conversation turn more than doubles abbreviation expansion accuracies compared to having no context, an effect that is more pronounced for longer phrases. Additionally, the robustness of models against typo noise can be enhanced through fine-tuning on noisy data.