# Weakly-supervised Neural Semantic Parsing with a Generative Ranker

arXiv: https://arxiv.org/abs/1808.07625 · HTML: https://mlsanity.com/paper/1808.07625/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2018.

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

- [LEVER: Learning to Verify Language-to-Code Generation with Execution](https://mlsanity.com/paper/2302.08468/) (2023)
- [Compositional Generalization in Multilingual Semantic Parsing over Wikidata](https://mlsanity.com/paper/2108.03509/) (2021)
- [Entailment-Preserving First-order Logic Representations in Natural Language Entailment](https://mlsanity.com/paper/2502.16757/) (2025)
- [A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering](https://mlsanity.com/paper/2106.07174/) (2021)
- [Knowledge Graph Question Answering via SPARQL Silhouette Generation](https://mlsanity.com/paper/2109.09475/) (2021)

## Abstract (arXiv)

Weakly-supervised semantic parsers are trained on utterance-denotation pairs, treating logical forms as latent. The task is challenging due to the large search space and spuriousness of logical forms. In this paper we introduce a neural parser-ranker system for weakly-supervised semantic parsing. The parser generates candidate tree-structured logical forms from utterances using clues of denotations. These candidates are then ranked based on two criterion: their likelihood of executing to the correct denotation, and their agreement with the utterance semantics. We present a scheduled training procedure to balance the contribution of the two objectives. Furthermore, we propose to use a neurally encoded lexicon to inject prior domain knowledge to the model. Experiments on three Freebase datasets demonstrate the effectiveness of our semantic parser, achieving results within the state-of-the-art range.