From f994b2de4eb8b85c704e7f1dcb7ed9ec83db9fab Mon Sep 17 00:00:00 2001 From: "W.P. McNeill" Date: Sat, 24 Jun 2017 16:20:29 -0500 Subject: [PATCH] Correct textual entialment nomenclature --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index c395f56..ea575cf 100644 --- a/README.md +++ b/README.md @@ -79,7 +79,7 @@ This achieved an accuracy of 83.71% on the validation split after 9 epochs of tr The [Stanford Natural Language Inference corpus](https://nlp.stanford.edu/projects/snli/) is a corpus for the recognizing textual entailment (RTE) task. -It labels a "text" sentence as either entailing, contradicting, or being neutral with respect to a "hypothesis" +It labels a "premise" sentence as either entailing, contradicting, or being neutral with respect to a "hypothesis" sentence. Bisemantic creates a model similar to that described in