yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-11-01 18:29:32 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README.rst

Browse Source
This commit is contained in:
Malte Pietsch 2019-11-25 11:07:32 +01:00 committed by GitHub
parent 5cad94756a
commit 277f24dcb8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 12 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
README.rst
View File

@ -6,27 +6,31 @@ Haystack — Natural Language Question Answering At Scale
Introduction
============
The performance of modern Question Answering Models (BERT, ALBERT ...) has seen drastic improvements within the last year enabling many new opportunities for finding information more efficiently. However, those models are usually designed to find answers within rather small text passages.
The performance of modern Question Answering Models (BERT, ALBERT ...) has seen drastic improvements within the last year enabling many new opportunities for finding information more efficiently. However, those models are usually designed to find answers within rather small text passages. **Haystack let's you scale QA models** to large collections of documents!
**Haystack let's you scale QA models** to large collections of documents!
The system is designed in a modular way and is tightly integrated with the `FARM <https://github.com/deepset-ai/FARM>`_ framework for training QA models.
Haystack is designed in a modular way and is tightly integrated with the `FARM <https://github.com/deepset-ai/FARM>`_ framework for training QA models.
Swap your models easily from BERT to roBERTa and scale the database from dev (Sqlite) to production (PostgreSQL, elasticsearch ...).
Core Features
==========
- Powerful models: Utilize all the latest transformer based models (BERT, ALBERT roBERTa ...)
- Modular: Avoid technical debt. With haystack you can easily switch to newer models once they get published.
- Developer friendly: Easy to debug, extend and modify
- Scalable: Switch from dev to production within minutes.
Components
==========
There are three major components for the question answering pipeline:
1. **Reader**: Powerful neural model that read through texts in detail to find an answer. Use diverse models like BERT, Roberta or XLNet trained via the `FARM <https://github.com/deepset-ai/FARM>`_ Framework on SQuaD like tasks. The Reader takes multiple passages of text as input and returns top-n answers with corresponding confidence scores.
2. **Retriever**: Fast, simple model that identify candidate passages from a large collection of documents. Algorithms include TF-IDF, which is similar to what's used in popular search systems like Elasticsearch. The Retriever helps to narrow down the scope for Reader to smaller units of text where a given question could be answered.
1. **Retriever**: Fast, simple model that identify candidate passages from a large collection of documents. Algorithms include TF-IDF, which is similar to what's used in popular search systems like Elasticsearch. The Retriever helps to narrow down the scope for Reader to smaller units of text where a given question could be answered.
2. **Reader**: Powerful neural model that read through texts in detail to find an answer. Use diverse models like BERT, Roberta or XLNet trained via the `FARM <https://github.com/deepset-ai/FARM>`_ Framework on SQuAD like tasks. The Reader takes multiple passages of text as input and returns top-n answers with corresponding confidence scores.
3. **Finder**: Glues together a Reader and a Retriever as a pipeline to provide an easy-to-use question answering interface.
4. Coming Soon: **Labeling Tool**
Quickstart
==========