Numerically Grounded Language Models for Semantic Error Correction
This addresses semantic error correction for applications like fact-checking and clinical reports, but it is incremental as it builds on existing methods with numerical grounding.
The paper tackled semantic error correction by grounding language models in numeric quantities, achieving a 33% perplexity reduction and a 5-point F1 score improvement on clinical reports.
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.