From b3b024133dcd61793659f5cf01cfa202ca5e5e28 Mon Sep 17 00:00:00 2001
From: Courtney Napoles <393791+cnap@users.noreply.github.com>
Date: Thu, 24 Oct 2019 11:00:21 -0700
Subject: [PATCH] Create README.md

---
 README.md | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)
 create mode 100644 README.md

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..a21127d
--- /dev/null
+++ b/README.md
@@ -0,0 +1,18 @@
+# Enabling Robust Grammatical Error Correction in New Domains: Data Sets, Metrics, and Analyses
+
+
+```
+@article{doi:10.1162/tacl\_a\_00282,
+author = {Napoles, Courtney and Nădejde, Maria and Tetreault, Joel},
+title = {Enabling Robust Grammatical Error Correction in New Domains: Data Sets, Metrics, and Analyses},
+journal = {Transactions of the Association for Computational Linguistics},
+volume = {7},
+number = {},
+pages = {551-566},
+year = {2019},
+doi = {10.1162/tacl\_a\_00282},
+URL = {https://doi.org/10.1162/tacl_a_00282},
+eprint = {https://doi.org/10.1162/tacl_a_00282},
+abstract = { Until now, grammatical error correction (GEC) has been primarily evaluated on text written by non-native English speakers, with a focus on student essays. This paper enables GEC development on text written by native speakers by providing a new data set and metric. We present a multiple-reference test corpus for GEC that includes 4,000 sentences in two new domains (formal and informal writing by native English speakers) and 2,000 sentences from a diverse set of non-native student writing. We also collect human judgments of several GEC systems on this new test set and perform a meta-evaluation, assessing how reliable automatic metrics are across these domains. We find that commonly used GEC metrics have inconsistent performance across domains, and therefore we propose a new ensemble metric that is robust on all three domains of text.}
+}
+```