Universal Sentence Encoder for English

Daniel Cer, Yinfei Yang, Sheng-yi Kong, Nan Hua, Nicole Limtiaco, Rhomni St. John, Noah Constant, Mario Guajardo-Cespedes, Steve Yuan, Chris Tar, Brian Strope, Ray Kurzweil
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations  
We present easy-to-use TensorFlow Hub sentence embedding models having good task transfer performance. Model variants allow for trade-offs between accuracy and compute resources. We report the relationship between model complexity, resources, and transfer performance. Comparisons are made with baselines without transfer learning and to baselines that incorporate word-level transfer. Transfer learning using sentence-level embeddings is shown to outperform models without transfer learning and
more » ... er learning and often those that use only word-level transfer. We show good transfer task performance with minimal training data and obtain encouraging results on word embedding association tests (WEAT) of model bias. † Corresponding authors: {cer, yinfeiy}@google.com 1 We describe our publicly released models. See Yang et al. (2018) and Henderson et al. (2017) for additional architectural details of models similar to those presented here. 2 https://www.tensorflow.org/hub/, Apache 2.0 license, with models available as saved TF graphs. import tensorflow_hub as hub embed = hub.Module("https://tfhub.dev/google/" "universal-sentence-encoder/2") embedding = embed(["Hello World!"])
doi:10.18653/v1/d18-2029 dblp:conf/emnlp/CerYKHLJCGYTSK18 fatcat:n3qpdqym7fasxgw5uhieilha7q