Multilingual Universal Sentence Encoder Q&A Retrieval

Stay organized with collections Save and categorize content based on your preferences.

View on Run in Google Colab View on GitHub Download notebook See TF Hub models

This is a demo for using Universal Encoder Multilingual Q&A model for question-answer retrieval of text, illustrating the use of question_encoder and response_encoder of the model. We use sentences from SQuAD paragraphs as the demo dataset, each sentence and its context (the text surrounding the sentence) is encoded into high dimension embeddings with the response_encoder. These embeddings are stored in an index built using the simpleneighbors library for question-answer retrieval.

On retrieval a random question is selected from the SQuAD dataset and encoded into high dimension embedding with the question_encoder and query the simpleneighbors index returning a list of approximate nearest neighbors in semantic space.

More models

You can find all currently hosted text embedding models here and all models that have been trained on SQuAD as well here.


Setup Environment

Setup common imports and functions

[nltk_data] Downloading package punkt to /home/kbuilder/nltk_data...
[nltk_data]   Unzipping tokenizers/

Run the following code block to download and extract the SQuAD dataset into:

  • sentences is a list of (text, context) tuples - each paragraph from the SQuAD dataset are splitted into sentences using nltk library and the sentence and paragraph text forms the (text, context) tuple.
  • questions is a list of (question, answer) tuples.

Download and extract SQuAD data

10455 sentences, 10552 questions extracted from SQuAD

Example sentence and context:


('The lockstep situation of the IPCC is having built a broad science consensus '
 'while states and governments still follow different, if not opposing goals.')


('The IPCC process on climate change and its efficiency and success has been '
 'compared with dealings with other environmental challenges (compare Ozone '
 'depletion and global warming). In case of the Ozone depletion global '
 'regulation based on the Montreal Protocol has been successful, in case of '
 'Climate Change, the Kyoto Protocol failed. The Ozone case was used to assess '
 'the efficiency of the IPCC process. The lockstep situation of the IPCC is '
 'having built a broad science consensus while states and governments still '
 'follow different, if not opposing goals. The underlying linear model of '
 'policy-making of more knowledge we have, the better the political response '
 'will be is being doubted.')

The following code block setup the tensorflow graph g and session with the Universal Encoder Multilingual Q&A model's question_encoder and response_encoder signatures.

Load model from tensorflow hub

The following code block compute the embeddings for all the text, context tuples and store them in a simpleneighbors index using the response_encoder.

Compute embeddings and build simpleneighbors index

Computing embeddings for 10455 sentences
0%|          | 0/104 [00:00<?, ?it/s]
simpleneighbors index for 10455 sentences built.

On retrieval, the question is encoded using the question_encoder and the question embedding is used to query the simpleneighbors index.

Retrieve nearest neighbors for a random question from SQuAD