![](\"https://github.com/UKPLab/arxiv2018-xling-sentence-embeddings/raw/master/figure-1.png?raw=true\")
\n\n\n## Sub-Projects\n\nThis repository contains different sub-projects:\n\n```\nSentence Embeddings Webserver
\nWe've started up a webserver that provides a simple HTTP API (with only one method) that enables\n you to generate concatenated p-mean sentence embeddings.
\nThe current loaded model is \"{{ model_name }}\".
\nAPI: Convert Sentences to Embeddings
\nThis is the only endpoint of our API. You can pass a list of sentences for which concatenated p-mean\n sentence embeddings will be generated. We recommend a maximum number of 500 sentences per request.\n Sentences should be already tokenized (tokens separated by spaces).
\n\nPOST /embed\n\n
| Parameter | \nDescription | \n
|---|---|
| conversion | \n\n A JSON string that contains input sentences and a list of embedding types and p-means that should\n be concatenated: \n\n{\n {%- if model_name.startswith('en') %}\n 'sentences': ['first_en sentence_en', 'second_en sentence_en'],\n {%- else %}\n 'sentences': ['first sentence', 'second sentence'],\n {%- endif %}\n 'embedding_types': [\n {%- for e in embeddings %}\n ('{{ e.alias }}', ['mean', 'min', 'max', 'p_mean_3']),\n {%- endfor %}\n ]\n}\n\n \n Available embeddings:\n {% for e in embeddings %} {{ e.alias }} {% endfor %}\n | \n
\n Response
One sentence embedding per line that corresponds to the ith input sentence.\n
Example Code: Python Request Builder
\nHere you can generate python code to query the API with the chosen embeddings and p-means!
\n\n| Generated Code | \n
|---|
| \n \n | \n
\n\n