Victor Dibia

Enable CQE as a standalone API - [ ] Export CQE as standalone api ... eg. import MLMExpander, .expand() - [ ] Support visualization in notebooks

- [ ] Currently, RelSnip provides lucene highlights to the reader. Can we further re-rank these highlights with BM25 query + highlight scores?. Explore implementation here and evaluate runtime costs....

- [ ] UI - [ ] rest end points - [ ] Reader - [x] Expander

## Improved Explanation Visualization Currently, we use a simple color density approach to visualize importance. Early feedback suggests this is helpful for the user immediately see the most important words/tokens,...

Perhaps a similar Class to [ElasticSearchRetriever](https://github.com/victordibia/neuralqa/blob/80e5e650a0787ffc3cc24fdb7ba17b6ec95d2ab7/neuralqa/retriever/elasticsearchretriever.py#L10) for Solr. - [ ] Method to run query with support for relsnip and all other kwargs

Currently, there are no in built security check to manage access to the neuralqa rest end point. On the minimum, we want to enable/disable open access to the rest endpoint...

- [ ] Currently score is a sum of the start and end token probabilities. This might not be optimal. - [ ] Current there is no text token preprocessing...

**v0.0.1** ## Backend - [x] Add sample questions/passages from yaml backend - [x] RelSnip toggle, also visualize RelSnip - [x] Tests for bad yaml - [ ] Revise probability scoring...

- [ ] Some reader requests can take longer than others (when reading long documents), implement a better "loading" visual cute. Right now it just says asking bert for answers...

- [x] Specify the fields to search from - [x] specify the main result field - [ ] specify any maximum retrieved length on the result field