# Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing

arXiv: https://arxiv.org/abs/2010.03546 · HTML: https://mlsanity.com/paper/2010.03546/

## Key facts

- Cited by 72 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2020.

## Built on by (most cited first, 30 of 72)

- [LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding](https://mlsanity.com/paper/2404.16710/) (2024)
- [Constrained Language Models Yield Few-Shot Semantic Parsers](https://mlsanity.com/paper/2104.08768/) (2021)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text](https://mlsanity.com/paper/2307.07696/) (2023)
- [Few-Shot Semantic Parsing with Language Models Trained On Code](https://mlsanity.com/paper/2112.08696/) (2021)
- [LLM Unlearning via Neural Activation Redirection](https://mlsanity.com/paper/2502.07218/) (2025)
- [Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models](https://mlsanity.com/paper/2311.09278/) (2023)
- [API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs](https://mlsanity.com/paper/2402.15491/) (2024)
- [Controllable Semantic Parsing via Retrieval Augmentation](https://mlsanity.com/paper/2110.08458/) (2021)
- [Program Transfer for Answering Complex Questions over Knowledge Bases](https://mlsanity.com/paper/2110.05743/) (2021)
- [Generative AI for Synthetic Data Generation: Methods, Challenges and the Future](https://mlsanity.com/paper/2403.04190/) (2024)
- [Meta Learning for Natural Language Processing: A Survey](https://mlsanity.com/paper/2205.01500/) (2022)
- [Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsing](https://mlsanity.com/paper/2110.15534/) (2021)
- [On the Domain Adaptation and Generalization of Pretrained Language Models: A Survey](https://mlsanity.com/paper/2211.03154/) (2022)
- [Mixture of Soft Prompts for Controllable Data Generation](https://mlsanity.com/paper/2303.01580/) (2023)
- [STOP: A dataset for Spoken Task Oriented Semantic Parsing](https://mlsanity.com/paper/2207.10643/) (2022)
- [The Power of Prompt Tuning for Low-Resource Semantic Parsing](https://mlsanity.com/paper/2110.08525/) (2021)
- [Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsing](https://mlsanity.com/paper/2104.07275/) (2021)
- [Label Semantic Aware Pre-training for Few-shot Text Classification](https://mlsanity.com/paper/2204.07128/) (2022)
- [RETRONLU: Retrieval Augmented Task-Oriented Semantic Parsing](https://mlsanity.com/paper/2109.10410/) (2021)
- [Generate-and-Retrieve: use your predictions to improve retrieval for semantic parsing](https://mlsanity.com/paper/2209.14899/) (2022)
- [A Survey of Intent Classification and Slot-Filling Datasets for Task-Oriented Dialog](https://mlsanity.com/paper/2207.13211/) (2022)
- [Answer Generation for Retrieval-based Question Answering Systems](https://mlsanity.com/paper/2106.00955/) (2021)
- [A Cross-Domain Benchmark for Active Learning](https://mlsanity.com/paper/2408.00426/) (2024)
- [Meta-Learning a Cross-lingual Manifold for Semantic Parsing](https://mlsanity.com/paper/2209.12577/) (2022)
- [Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?](https://mlsanity.com/paper/2302.08143/) (2023)
- [Low-Resource Task-Oriented Semantic Parsing via Intrinsic Modeling](https://mlsanity.com/paper/2104.07224/) (2021)
- [Compositional Task-Oriented Parsing as Abstractive Question Answering](https://mlsanity.com/paper/2205.02068/) (2022)
- [Dialog2API: Task-Oriented Dialogue with API Description and Example Programs](https://mlsanity.com/paper/2212.09946/) (2022)
- [Semantic Parsing in Task-Oriented Dialog with Recursive Insertion-based Encoder](https://mlsanity.com/paper/2109.04500/) (2021)

## Abstract (arXiv)

Task-oriented semantic parsing is a critical component of virtual assistants, which is responsible for understanding the user's intents (set reminder, play music, etc.). Recent advances in deep learning have enabled several approaches to successfully parse more complex queries (Gupta et al., 2018; Rongali et al.,2020), but these models require a large amount of annotated training data to parse queries on new domains (e.g. reminder, music). In this paper, we focus on adapting task-oriented semantic parsers to low-resource domains, and propose a novel method that outperforms a supervised neural model at a 10-fold data reduction. In particular, we identify two fundamental factors for low-resource domain adaptation: better representation learning and better training techniques. Our representation learning uses BART (Lewis et al., 2019) to initialize our model which outperforms encoder-only pre-trained representations used in previous work. Furthermore, we train with optimization-based meta-learning (Finn et al., 2017) to improve generalization to low-resource domains. This approach significantly outperforms all baseline methods in the experiments on a newly collected multi-domain task-oriented semantic parsing dataset (TOPv2), which we release to the public.