Link to Universal Sentence Encoder paper from its TF-hub module page.

PiperOrigin-RevId: 192634552

docs/modules/google/universal-sentence-encoder/1.md

@@ -22,7 +22,8 @@ semantic similarity, and the results can be seen in the [example notebook](https
 To learn more about text embeddings, refer to the [TensorFlow Embeddings](https://www.tensorflow.org/programmers_guide/embedding)
 documentation. Our encoder differs from word level embedding models in that we
 train on a number of natural language prediction tasks that require modeling the
-meaning of word sequences rather than just individual words.
+meaning of word sequences rather than just individual words. Details are
+available in the paper "Universal Sentence Encoder" [1].
 
 #### Example use
 
@@ -66,3 +67,10 @@ that can embed sentences. The Universal Sentence Encoder was partly trained with
 custom text classification tasks in mind. It can be trained to perform a wide
 variety of classification tasks often with a very small amount of labeled
 examples.
+
+## References
+
+[1] Daniel Cer, Yinfei Yang, Sheng-yi Kong, Nan Hua, Nicole Limtiaco,
+Rhomni St. John, Noah Constant, Mario Guajardo-Céspedes, Steve Yuan, Chris Tar,
+Yun-Hsuan Sung, Brian Strope, Ray Kurzweil. [Universal Sentence Encoder](https://arxiv.org/abs/1803.11175).
+arXiv:1803.11175, 2018.