Point to the renamed WebNLG text-to-graph repository

README.md

@@ -15,7 +15,7 @@ tags:
 
 This T5-large model converts English text into subject–relation–object triples. It implements the WebNLG T2G.CE setting of [Dognin et al. (2021)](https://aclanthology.org/2021.emnlp-main.83/), using cross-entropy fine-tuning.
 
-The first author of the [XQDT paper](https://huggingface.co/papers/2608.29948) reproduced ReGen T2G.CE for use as a base text-to-data model in that study. The [reproduction repository](https://github.com/guihuzhang/bt5-regen-reproduction) contains the code, saved predictions, and evaluation scripts.
+The first author of the [XQDT paper](https://huggingface.co/papers/2608.29948) reproduced ReGen T2G.CE for use as a base text-to-data model in that study. The [reproduction repository](https://github.com/guihuzhang/bt5-regen-text-to-graph) contains the code, saved predictions, and evaluation scripts.
 
 The checkpoint is epoch 3 of the continuation run. Its saved predictions on 2,155 WebNLG 2020 English test examples give Exact precision 70.35, recall 72.18, and F1 71.07, using five-beam decoding. For CE on the same task, [Table 2 of the ReGen paper](https://aclanthology.org/2021.emnlp-main.83.pdf#page=7) reports 72.3 Exact F1, while the example run in the [IBM training guide](https://github.com/IBM/regen/blob/main/docs/train_t2g_webnlg.md#overview) scores 70.11.