# Web Question Answering with Neurosymbolic Program Synthesis

arXiv: https://arxiv.org/abs/2104.07162 · HTML: https://mlsanity.com/paper/2104.07162/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Apr 2021.

## Built on by (most cited first, 11 of 11)

- [Scallop: A Language for Neurosymbolic Programming](https://mlsanity.com/paper/2304.04812/) (2023)
- [Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review](https://mlsanity.com/paper/2202.12205/) (2022)
- [From Perception to Programs: Regularize, Overparameterize, and Amortize](https://mlsanity.com/paper/2206.05922/) (2022)
- [NaviQAte: Functionality-Guided Web Application Navigation](https://mlsanity.com/paper/2409.10741/) (2024)
- [Automatic Synthesis of Diverse Weak Supervision Sources for Behavior Analysis](https://mlsanity.com/paper/2111.15186/) (2021)
- [DiLogics: Creating Web Automation Programs With Diverse Logics](https://mlsanity.com/paper/2308.05828/) (2023)
- [TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pages](https://mlsanity.com/paper/2205.06435/) (2022)
- [Uncertainty Quantification for Neurosymbolic Programs via Compositional Conformal Prediction](https://mlsanity.com/paper/2405.15912/) (2024)
- [Lobster: A GPU-Accelerated Framework for Neurosymbolic Programming](https://mlsanity.com/paper/2503.21937/) (2025)
- [Efficient Bottom-Up Synthesis for Programs with Local Variables](https://mlsanity.com/paper/2311.03705/) (2023)
- [MetaSpace: Metamorphic Testing for Spatial Cognition in Embodied Agents](https://mlsanity.com/paper/2608.07533/) (2026)

## Abstract (arXiv)

In this paper, we propose a new technique based on program synthesis for extracting information from webpages. Given a natural language query and a few labeled webpages, our method synthesizes a program that can be used to extract similar types of information from other unlabeled webpages. To handle websites with diverse structure, our approach employs a neurosymbolic DSL that incorporates both neural NLP models as well as standard language constructs for tree navigation and string manipulation. We also propose an optimal synthesis algorithm that generates all DSL programs that achieve optimal F1 score on the training examples. Our synthesis technique is compositional, prunes the search space by exploiting a monotonicity property of the DSL, and uses transductive learning to select programs with good generalization power. We have implemented these ideas in a new tool called WebQA and evaluate it on 25 different tasks across multiple domains. Our experiments show that WebQA significantly outperforms existing tools such as state-of-the-art question answering models and wrapper induction systems.