aagohary/canard
Repo for the question-in-context rewriting baseline presented in Elgohary et al. "Can you unpack that? Learning to rewrite questions-in-context", EMNLP 2019.
This project helps clarify follow-up questions in conversations or information retrieval systems. It takes a follow-up question and the preceding conversational context (like previous questions and answers) and outputs a standalone, rephrased version of the follow-up question. This is useful for anyone building or managing conversational AI, chatbots, or search interfaces that need to understand nuanced user queries.
No commits in the last 6 months.
Use this if you need to transform context-dependent questions into independent, unambiguous queries for better understanding or processing by downstream systems.
Not ideal if you are looking for a general-purpose natural language generation tool or a system that answers questions directly.
Stars
24
Forks
6
Language
Perl
License
—
Category
Last pushed
May 20, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/aagohary/canard"
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.
hsinyuan-huang/FlowQA
Implementation of conversational QA model: FlowQA (with slight improvement)
allenai/aokvqa
Official repository for the A-OKVQA dataset