Universal Sentence Encoder
arxiv.org
Universal Sentence Encoder
1–10 of 36 posts
Re: Universal Sentence Encoder
#2>Our pre-trained sentence encoding models are made freely available for download and on TF Hub.
what is tf hub? I assume it stands for tensor flow hub but what is that
Re: Universal Sentence Encoder
#3>Our pre-trained sentence encoding models are made freely available for download and on TF Hub. what is tf hub? I assume it stands for tensor flow hub but what is that
It looks like an internal site, this is the link it is referring to: https://tfhub.dev/google/universal-sentence-encoder/1
Re: Universal Sentence Encoder
#4>Our pre-trained sentence encoding models are made freely available for download and on TF Hub. what is tf hub? I assume it stands for tensor flow hub but what is that
It looks like an internal site, this is the link it is referring to: https://tfhub.dev/google/universal-sentence-encoder/1
404?
Re: Universal Sentence Encoder
#5Re: Universal Sentence Encoder
#6“We present models for encoding sentences into embedding vectors that specifically target transfer learning to other NLP tasks. The models are efficient and result in accurate performance on diverse transfer tasks. Two variants of the encoding models allow for trade-offs between accuracy and compute resources. For both variants, we investigate and report the relationship between model complexity, resource consumption, the availability of transfer task training data, and task performance. Comparisons are made with baselines that use word level transfer learning via pretrained word embeddings as well as baselines do not use any transfer learning. We find that transfer learning using sentence embeddings tends to outperform word level transfer. With transfer learning via sentence embeddings, we observe surprisingly good performance with minimal amounts of supervised training data for a transfer task. We obtain encouraging results on Word Embedding Association Tests (WEAT) targeted at detecting model bias. Our pre-trained sentence encoding models are made freely available for download and on TF Hub.”
Awesome. Now what does all that mean in English?
Re: Universal Sentence Encoder
#7"..transfer learning to other NLP tasks" – NLP as in neuro-linguistic programming?
If so, can someone explain how this project is related to NLP? Thanks!
Re: Universal Sentence Encoder
#8"..transfer learning to other NLP tasks" – NLP as in neuro-linguistic programming? If so, can someone explain how this project is related to NLP? Thanks!
Natural language processing/parsing
Re: Universal Sentence Encoder
#9>Our pre-trained sentence encoding models are made freely available for download and on TF Hub. what is tf hub? I assume it stands for tensor flow hub but what is that
Seems to be model-zoo with tight tf integration
Seems to be announcing today at the TF summit this afternoon: https://www.tensorflow.org/dev-summit/schedule/
pip/github links not yet activated: https://pypi.python.org/pypi/tensorflow-hub/0.1.0
Re: Universal Sentence Encoder
#10“We present models for encoding sentences into embedding vectors that specifically target transfer learning to other NLP tasks. The models are efficient and result in accurate performance on diverse transfer tasks. Two variants of the encoding models allow for trade-offs between accuracy and compute resources. For both variants, we investigate and report the relationship between model complexity, resource consumption…
They made a way to take any sentence, and output a small array of numbers that represent its essence. You can use their model to find the essence of your own sentences. And then use it either directly (e.g. compare the essence of two sentences to see if they're saying roughly the same thing) or use it as a starting point for the model you need (e.g. if you're building a system to convert English sentences into French, your neural network might generate the essence of the English sentence as part of its work. By using the pre-trained model, you have a better starting point for that part of the network than just random numbers, so your training time will be greatly reduced).