Skip to content
conftrace_
2018 NAACL NAACL 2018

Reference-less Measure of Faithfulness for Grammatical Error Correction

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 - Artificial Intelligence and Natural Language Processing
🧭 Keyword Pioneer - text evaluation
🐣 Hot Topic Early Bird - grammatical error correction

More from NAACL 2018

All NAACL 2018 papers →