# Numerically Grounded Language Models for Semantic Error Correction

arXiv: https://arxiv.org/abs/1608.04147 · HTML: https://mlsanity.com/paper/1608.04147/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2016.

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

- [Grounding 'Grounding' in NLP](https://mlsanity.com/paper/2106.02192/) (2021)
- [Mathematical Language Models: A Survey](https://mlsanity.com/paper/2312.07622/) (2023)
- [A Survey on Mathematical Reasoning and Optimization with Large Language Models](https://mlsanity.com/paper/2503.17726/) (2025)
- [Data Cleaning and Machine Learning: A Systematic Literature Review](https://mlsanity.com/paper/2310.01765/) (2023)
- [CONE: Embeddings for Complex Numerical Data Preserving Unit and Variable Semantics](https://mlsanity.com/paper/2603.04741/) (2026)

## Abstract (arXiv)

Semantic error detection and correction is an important task for applications such as fact checking, speech-to-text or grammatical error correction. Current approaches generally focus on relatively shallow semantics and do not account for numeric quantities. Our approach uses language models grounded in numbers within the text. Such groundings are easily achieved for recurrent neural language model architectures, which can be further conditioned on incomplete background knowledge bases. Our evaluation on clinical reports shows that numerical grounding improves perplexity by 33% and F1 for semantic error correction by 5 points when compared to ungrounded approaches. Conditioning on a knowledge base yields further improvements.