Numerically Grounded Language Models for Semantic Error Correction

08/14/2016
by   Georgios P. Spithourakis, et al.
0

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 correction by 5 points when compared to ungrounded approaches. Conditioning on a knowledge base yields further improvements.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset