Spithourakis, GP; Augenstein, I; Riedel, S; (2016) Numerically Grounded Language Models for Semantic Error Correction. In: Conference on Empirical Methods in Natural Language Processing: Conference Proceedings. (pp. pp. 987-992). Association for Computational Linguistics (ACL): Austin, TX, USA.

Preview

Text Augenstein_Numerically Grounded Language Models_.pdf - Accepted Version Download (414kB) | Preview

Abstract

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.

Download activity - last month

Export as XMLJSONCSV

Download activity - last 12 months

Export as JSONXMLCSV

Downloads by country - last 12 months

Export as XMLJSONCSV

Archive Staff Only

View Item