awesome-qa
github.com/seriousran/awesome-qa ↗😎 A curated list of the Question Answering (QA)
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me arxiv resources from awesome-qa"
Installation instructions →What's inside
Recent Trends
- A BERT Baseline for the Natural QuestionsArxiv
- A Discrete Hard EM Approach for Weakly Supervised Question AnsweringEMNLP-IJCNLP 2019
- ALBERT: A Lite BERT for Self-supervised Learning of Language RepresentationsRecent Language Models
- Answering Complex Open-domain Questions Through Iterative Query GenerationEMNLP-IJCNLP 2019
- BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment AnalysisArxiv
- BERT with History Answer Embedding for Conversational Question AnsweringArxiv
Datasets
- AI2 Science Questions v2.1(2017)
- "Analyzing Language Learned by an Active Question Answering Agent"Google AI's publication within 5 years
- "An efficient framework for learning sentence representations"Google AI's publication within 5 years
- "An Overview of Microsoft Deep QA System on Stanford WebQuestions Benchmark"MS Research's publication within 5 years
- "Ask the Right Questions: Active Question Reformulation with Reinforcement Learning"Google AI's publication within 5 years
- "Building Large Machine Reading-Comprehension Datasets using Paragraph Vectors"Google AI's publication within 5 years
Publications
- "A survey on question answering technology from an information retrieval perspective"
- "Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks"
- "Deep Joint Entity Disambiguation with Local Neural Attention"
- "Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions"
- https://GitHub.com/matthewfl/nlp-entity-convnet
- "Introduction to “This is Watson"
Codes
- BERT
A new language representation model which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations by jointly conditioning on both left and right context in all layers.
- BiDAF
Bi-Directional Attention Flow (BIDAF) network is a multi-stage hierarchical process that represents the context at different levels of granularity and uses bi-directional attention flow mechanism to obtain a query-aware context representation without early summarization.
- DrQA
DrQA is a system for reading comprehension applied to open-domain question answering.
- PaperRecent Language Models
- Paper
- Paper
Links
Systems
- Facebook DrQA
Applied to the SQuAD1.0 dataset. The SQuAD2.0 dataset has released. but DrQA is not tested yet.
- IBM Watson
Has state-of-the-arts performance.
- MIT media lab's Knowledge graph
Is a freely-available semantic network, designed to help computers understand the meanings of words that people use.
Events
Showing a sample of 125 resources. View the full list on GitHub →