# Learning Semantic Parsers from Denotations with Latent Structured Alignments and Abstract Programs

arXiv: https://arxiv.org/abs/1909.04165 · HTML: https://mlsanity.com/paper/1909.04165/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Sep 2019.

## Built on by (most cited first, 26 of 26)

- [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://mlsanity.com/paper/2107.07653/) (2021)
- [UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models](https://mlsanity.com/paper/2201.05966/) (2022)
- [Binding Language Models in Symbolic Languages](https://mlsanity.com/paper/2210.02875/) (2022)
- [Large Language Models are few(1)-shot Table Reasoners](https://mlsanity.com/paper/2210.06710/) (2022)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect](https://mlsanity.com/paper/2208.10099/) (2022)
- [S2SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers](https://mlsanity.com/paper/2203.06958/) (2022)
- [A Survey on Table Question Answering: Recent Advances](https://mlsanity.com/paper/2207.05270/) (2022)
- [TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition](https://mlsanity.com/paper/2404.10150/) (2024)
- [Capturing Row and Column Semantics in Transformer Based Question Answering over Tables](https://mlsanity.com/paper/2104.08303/) (2021)
- [OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering](https://mlsanity.com/paper/2207.03637/) (2022)
- [ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples](https://mlsanity.com/paper/2210.12374/) (2022)
- [NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization](https://mlsanity.com/paper/2406.17961/) (2024)
- [Weakly Supervised Text-to-SQL Parsing through Question Decomposition](https://mlsanity.com/paper/2112.06311/) (2021)
- [From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuning](https://mlsanity.com/paper/2304.07995/) (2023)
- [DoT: An efficient Double Transformer for NLP tasks with tables](https://mlsanity.com/paper/2106.00479/) (2021)
- [Learning from Executions for Semantic Parsing](https://mlsanity.com/paper/2104.05819/) (2021)
- [SPARQLing Database Queries from Intermediate Question Decompositions](https://mlsanity.com/paper/2109.06162/) (2021)
- [Optimization Techniques for Unsupervised Complex Table Reasoning via Self-Training Framework](https://mlsanity.com/paper/2212.10097/) (2022)
- [Measuring and Mitigating Constraint Violations of In-Context Learning for Utterance-to-API Semantic Parsing](https://mlsanity.com/paper/2305.15338/) (2023)
- [Bridge the Gap between Language models and Tabular Understanding](https://mlsanity.com/paper/2302.09302/) (2023)
- [A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering](https://mlsanity.com/paper/2106.07174/) (2021)
- [Weakly-Supervised Questions for Zero-Shot Relation Extraction](https://mlsanity.com/paper/2301.09640/) (2023)
- [Structural Deep Encoding for Table Question Answering](https://mlsanity.com/paper/2503.01457/) (2025)
- [Weakly Supervised Semantic Parsing with Execution-based Spurious Program Filtering](https://mlsanity.com/paper/2311.01161/) (2023)
- [Around the GLOBE: Numerical Aggregation Question-Answering on Heterogeneous Genealogical Knowledge Graphs with Deep Neural Networks](https://mlsanity.com/paper/2307.16208/) (2023)

## Abstract (arXiv)

Semantic parsing aims to map natural language utterances onto machine interpretable meaning representations, aka programs whose execution against a real-world environment produces a denotation. Weakly-supervised semantic parsers are trained on utterance-denotation pairs treating programs as latent. The task is challenging due to the large search space and spuriousness of programs which may execute to the correct answer but do not generalize to unseen examples. Our goal is to instill an inductive bias in the parser to help it distinguish between spurious and correct programs. We capitalize on the intuition that correct programs would likely respect certain structural constraints were they to be aligned to the question (e.g., program fragments are unlikely to align to overlapping text spans) and propose to model alignments as structured latent variables. In order to make the latent-alignment framework tractable, we decompose the parsing task into (1) predicting a partial "abstract program" and (2) refining it while modeling structured alignments with differential dynamic programming. We obtain state-of-the-art performance on the WIKITABLEQUESTIONS and WIKISQL datasets. When compared to a standard attention baseline, we observe that the proposed structured-alignment mechanism is highly beneficial.