• Home
  • Search
  • Training Naturalized Semantic Parsers with Very Little Data
  • Cite Icon11
  • https://doi.org/10.24963/ijcai.2022/604Copy DOI Icon

Training Naturalized Semantic Parsers with Very Little Data

  • Jul 1, 2022
  • Subendhu Rongali +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Semantic parsing is an important NLP problem, particularly for voice assistants such as Alexa and Google Assistant. State-of-the-art (SOTA) semantic parsers are seq2seq architectures based on large language models that have been pretrained on vast amounts of text. To better leverage that pretraining, recent work has explored a reformulation of semantic parsing whereby the output sequences are themselves natural language sentences, but in a controlled fragment of natural language. This approach delivers strong results, particularly for few-shot semantic parsing, which is of key importance in practice and the focus of our paper. We push this line of work forward by introducing an automated methodology that delivers very significant additional improvements by utilizing modest amounts of unannotated data, which is typically easy to obtain. Our method is based on a novel synthesis of four techniques: joint training with auxiliary unsupervised tasks; constrained decoding; self-training; and paraphrasing. We show that this method delivers new SOTA few-shot performance on the Overnight dataset, particularly in very low-resource settings, and very compelling few-shot results on a new semantic parsing dataset.

Similar Papers
  • Conference Article

Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm

  • Jan 01, 2024
  • Hexuan Deng +4
  • Research Article
  • Citations26

Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey

  • Nov 01, 2024
  • IEEE Transactions on Knowledge and Data Engineering
  • Weixu Zhang +8
  • Conference Article

SQUAB: Evaluating LLM robustness to Ambiguous and Unanswerable Questions in Semantic Parsing

  • Jan 01, 2025
  • Simone Papicchio +2
  • Research Article
  • Citations3

Large Language Models for Heterogeneous Catalysis

  • Sep 01, 2025
  • WIREs Computational Molecular Science
  • Yiwen Yao +5
  • Conference Article
  • Citations1

A Question Answering System for Unstructured Table Images

  • Oct 17, 2021
  • Wenyuan Xue +6
  • PDF
  • Conference Article
  • Citations29

Semantic Parsing for Textual Entailment

  • Jan 01, 2015
  • Elisabeth Lien +1
  • Research Article

Evaluating gpt-4 for zero-shot classification of bleeding and clotting events: Can large language models serve as second reviewers?

  • Nov 03, 2025
  • Blood
  • Samantha Rizzo +5
  • Research Article
  • Citations51

Large language models for biomedicine: foundations, opportunities, challenges, and best practices.

  • Apr 24, 2024
  • Journal of the American Medical Informatics Association : JAMIA
  • Satya S Sahoo +8
  • Research Article
  • Citations1

A Hybrid Neuro-Symbolic Pipeline for Coreference Resolution and AMR-Based Semantic Parsing

  • Jun 24, 2025
  • Information
  • Christos Papakostas +3
  • Research Article
  • Citations5

DG‐based SPO tuple recognition using self‐attention M‐Bi‐LSTM

  • Nov 29, 2021
  • ETRI Journal
  • Joon‐Young Jung
  • Conference Article
  • Citations3

On the use of Large Language Models to Detect Brazilian Politics Fake News

  • Nov 17, 2024
  • Marcos P S Gôlo +6
  • Conference Article
  • Citations16

HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMs

  • Jan 01, 2024
  • Pranoy Panda +4
  • Research Article
  • Citations1

Logical and Physical Optimizations for SQL Query Execution over Large Language Models

  • Jun 17, 2025
  • Proceedings of the ACM on Management of Data
  • Dario Satriani +5
  • Research Article
  • Citations67

The life cycle of large language models in education: A framework for understanding sources of bias

  • Jul 12, 2024
  • British Journal of Educational Technology
  • Jinsook Lee +4
  • Video Transcripts

One Semantic Parser to Parse Them All: Sequence to Sequence Multi-Task Learning on Semantic Parsing Datasets

  • Jul 22, 2021
  • Underline Science Inc.
  • Emilio Monti +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.