hsinyuan-huang/FlowQA
Implementation of conversational QA model: FlowQA (with slight improvement)
Extends single-turn QA models to handle multi-turn conversational contexts by modeling dialog flow through history, with support for QuAC and CoQA datasets. Built on PyTorch with preprocessing pipelines for both datasets and configurable answer marking via explicit dialog context flags. Includes answer thresholding during inference and modular training/prediction scripts for easy experimentation and extension.
196 stars. No commits in the last 6 months.
Stars
196
Forks
54
Language
Python
License
—
Category
Last pushed
May 21, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/hsinyuan-huang/FlowQA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
asahi417/lm-question-generation
Multilingual/multidomain question generation datasets, models, and python library for question...
SparkJiao/SLQA
An Unofficial Pytorch Implementation of Multi-Granularity Hierarchical Attention Fusion Networks...
MurtyShikhar/Question-Answering
TensorFlow implementation of Match-LSTM and Answer pointer for the popular SQuAD dataset.
allenai/aokvqa
Official repository for the A-OKVQA dataset
DevSinghSachan/emdr2
Code and Models for the paper "End-to-End Training of Multi-Document Reader and Retriever for...