awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
facebookresearch avatar

facebookresearch/DrQAArchived

0
View on GitHub↗
4,468 stars·882 forks·Python·9 views

DrQA

DrQA is an open-domain question answering system that retrieves relevant documents from a large corpus and extracts specific answers to natural language questions. It is implemented as a neural network system that combines a document retrieval engine with a machine reading comprehension model.

The system utilizes a two-stage pipeline architecture. A coarse-grained document retriever uses weighted word vectors to identify potential documents, while a fine-grained machine reading comprehension model identifies and extracts the exact text span containing the answer.

The project also includes a supervised natural language processing dataset generator. This tool creates training examples by matching question-answer pairs with supporting paragraphs using automated string heuristics.

The codebase provides additional capabilities for text processing and tokenization to prepare raw text for neural network processing.

Features

  • Question Answering Systems - An open-domain question answering system that retrieves relevant documents and extracts specific answers.
  • Answer Extraction Logics - Uses a neural model to isolate specific answer spans from a larger body of unstructured text.
  • Answer Span Prediction - Employs a neural model to predict the exact start and end positions of an answer span within a text segment.
  • Reading Comprehension - Uses neural networks to identify and extract specific answer spans from provided text.
  • Two-Stage Retrieval Pipelines - Implements a two-stage pipeline combining coarse-grained document retrieval with fine-grained reading comprehension.
  • Semantic Document Retrieval - Uses vector embeddings for semantic document retrieval within a large unstructured corpus.
  • Corpus Search - Retrieves relevant documents from a large text collection based on user queries.
  • Document Search Engines - Implements a search engine that uses weighted word vectors to retrieve documents containing potential answers.
  • Dense Vector Retrieval - Implements a retrieval mechanism using weighted word representations to identify relevant documents in a large corpus.
  • Training Data Synthesis - Provides a tool for creating training examples by matching question-answer pairs with supporting paragraphs.
  • Training Pair Generators - Synthesizes training data by matching question-answer pairs with corresponding supporting documents.
  • Automated Training Example Generation - Ships an automated process for creating training examples using string heuristics to match questions and paragraphs.
  • Natural Language Processing - System for reading Wikipedia to answer open-domain questions.
  • Natural Language Understanding - System for open-domain question answering over large document collections.
  • Question Answering - Open-domain question answering system for Wikipedia data.
  • Question and Answering - Listed in the “Question and Answering” section of the The Incredible Pytorch awesome list.

Star history

Star history chart for facebookresearch/drqaStar history chart for facebookresearch/drqa

How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Frequently asked questions

What does facebookresearch/drqa do?

DrQA is an open-domain question answering system that retrieves relevant documents from a large corpus and extracts specific answers to natural language questions. It is implemented as a neural network system that combines a document retrieval engine with a machine reading comprehension model.

What are the main features of facebookresearch/drqa?

The main features of facebookresearch/drqa are: Question Answering Systems, Answer Extraction Logics, Answer Span Prediction, Reading Comprehension, Two-Stage Retrieval Pipelines, Semantic Document Retrieval, Corpus Search, Document Search Engines.

What are some open-source alternatives to facebookresearch/drqa?

Open-source alternatives to facebookresearch/drqa include: deeppavlov/deeppavlov — DeepPavlov is a conversational AI framework and deep learning NLP library designed for building end-to-end dialogue… zihangdai/xlnet — This project is a natural language processing framework focused on a generalized autoregressive pretrainer designed… microsoft/nlp-recipes — nlp-recipes is a collection of implementation guides and reference templates for applying natural language processing… axa-group/nlp.js — nlp.js is a JavaScript natural language processing library and development framework used to build natural language… datawhalechina/so-large-lm — This project is a comprehensive educational curriculum and structured learning path covering the full lifecycle of… future-house/paper-qa — Paper-qa is a retrieval augmented generation system designed for question answering and analysis of scientific…

Open-source alternatives to DrQA

Similar open-source projects, ranked by how many features they share with DrQA.
  • deeppavlov/deeppavlovdeeppavlov avatar

    deeppavlov/DeepPavlov

    6,985View on GitHub↗

    DeepPavlov is a conversational AI framework and deep learning NLP library designed for building end-to-end dialogue systems and chatbots. It functions as an NLP pipeline orchestrator that allows users to compose pre-trained models and text processing components into sequential data flows for complex linguistic tasks. The system is distinguished by its ability to act as a chatbot deployment server, exposing trained conversational models as web services via REST and Socket APIs. It utilizes JSON-based pipeline configurations and dynamic variable interpolation to decouple model logic from infras

    Pythonaiartificial-intelligencebot
    View on GitHub↗6,985
  • zihangdai/xlnetzihangdai avatar

    zihangdai/xlnet

    6,182View on GitHub↗

    This project is a natural language processing framework focused on a generalized autoregressive pretrainer designed for unsupervised language representation. It implements a language model that combines permutation-based training with a Transformer-XL backbone to function as a long-context text processor. The system is distinguished by its ability to handle text sequences that exceed standard length limits through the use of segment-level recurrence and relative positional encoding. It scales high-performance pretraining across multiple GPUs and TPU clusters using distributed training impleme

    Python
    View on GitHub↗6,182
  • microsoft/nlp-recipesmicrosoft avatar

    microsoft/nlp-recipes

    6,436View on GitHub↗

    nlp-recipes is a collection of implementation guides and reference templates for applying natural language processing techniques to real-world tasks. It provides standardized workflows and code examples for developing NLP pipelines, from dataset preparation and model training to performance evaluation. The project focuses on the practical application of transformer-based models, offering patterns for fine-tuning pretrained architectures for tasks such as text classification, named entity recognition, and question answering. It also includes a toolkit for model interpretability, allowing users

    Python
    View on GitHub↗6,436
  • axa-group/nlp.jsaxa-group avatar

    axa-group/nlp.js

    6,574View on GitHub↗

    nlp.js is a JavaScript natural language processing library and development framework used to build natural language understanding engines. It provides a toolkit for creating local machine learning models for intent classification and acts as a multilingual text processor that detects languages and normalizes text across various dialects. The framework distinguishes itself by supporting local execution on both servers and mobile devices, enabling chatbot functionality without an internet connection. It features a specialized system for conversational slot filling to collect mandatory informati

    JavaScriptbotbotschatbot
    View on GitHub↗6,574
  • See all 30 alternatives to DrQA→