2018
NAACL
NAACL 2018
Reference-less Measure of Faithfulness for Grammatical Error Correction
Abstract
AbstractWe propose USim, a semantic measure for Grammatical Error Correction (that measures the semantic faithfulness of the output to the source, thereby complementing existing reference-less measures (RLMs) for measuring the output’s grammaticality. USim operates by comparing the semantic symbolic structure of the source and the correction, without relying on manually-curated references. Our experiments establish the validity of USim, by showing that the semantic structures can be consistently applied to ungrammatical text, that valid corrections obtain a high USim similarity score to the source, and that invalid corrections obtain a lower score.
🌉
Interdisciplinary Bridge
— Machine Learning and Natural Language Processing
📈
Trend Setter
— Evaluation
🧭
Keyword Pioneer
— semantic faithfulness
🐣
Hot Topic Early Bird
— grammatical error correction
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Security & Privacy, Speech & Audio