From 506effdf828895360e9843f80bf685bb5db287f6 Mon Sep 17 00:00:00 2001 From: nlpfun Date: Wed, 1 Dec 2021 01:29:04 +0800 Subject: [PATCH] Update README.md --- README.md | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/README.md b/README.md index 26c1bdf..7c7c7e4 100644 --- a/README.md +++ b/README.md @@ -440,6 +440,15 @@ Bertalign achieves 0.94 F1 score on Text+Berg, which is 4 points higher than the -g data/text+berg/gold ``` +``` +--------------------------------- +| | Strict | Lax | +| Precision | 0.869 | 0.993 | +| Recall | 0.857 | 0.984 | +| F1 | 0.863 | 0.988 | + --------------------------------- +``` + This F1 score is 4 points lower than that reported in [Thompson & Koehn 2019](https://aclanthology.org/D19-1136/). The original Vecalign paper uses [LASER](https://github.com/facebookresearch/LASER) to embed the source and target texts while we use [sentence-transformers](https://github.com/UKPLab/sentence-transformers), which may have caused the gap. ## Post-processing