diff --git a/site/en/hub/tutorials/semantic_similarity_with_tf_hub_universal_encoder.ipynb b/site/en/hub/tutorials/semantic_similarity_with_tf_hub_universal_encoder.ipynb
index 47d99947ff..9bde607b4a 100644
--- a/site/en/hub/tutorials/semantic_similarity_with_tf_hub_universal_encoder.ipynb
+++ b/site/en/hub/tutorials/semantic_similarity_with_tf_hub_universal_encoder.ipynb
@@ -260,7 +260,7 @@
       "source": [
         "## Evaluation: STS (Semantic Textual Similarity) Benchmark\n",
         "\n",
-        "The [**STS Benchmark**](https://ixa2.si.ehu.es/stswiki/index.php/STSbenchmark) provides an intrinsic evaluation of the degree to which similarity scores computed using sentence embeddings align with human judgements. The benchmark requires systems to return similarity scores for a diverse selection of sentence pairs. [Pearson correlation](https://en.wikipedia.org/wiki/Pearson_correlation_coefficient) is then used to evaluate the quality of the machine similarity scores against human judgements."
+        "The [**STS Benchmark**](https://ixa2.si.ehu.eus/stswiki/stswiki/index.php/Special:Random.html) provides an intrinsic evaluation of the degree to which similarity scores computed using sentence embeddings align with human judgements. The benchmark requires systems to return similarity scores for a diverse selection of sentence pairs. [Pearson correlation](https://en.wikipedia.org/wiki/Pearson_correlation_coefficient) is then used to evaluate the quality of the machine similarity scores against human judgements."
       ]
     },
     {