McGill-NLP/topiocqa
Code and data for reproducing baselines for TopiOCQA, an open-domain conversational question-answering dataset
This project helps researchers and developers working on conversational AI systems to build question-answering models that can handle changes in conversation topics. It takes a series of user questions and previous answers, processes them to understand the context, and outputs relevant text passages that contain the answer, even when the conversation shifts to a new subject. It's designed for anyone building sophisticated open-domain chatbots or intelligent assistants.
No commits in the last 6 months.
Use this if you are developing conversational AI models and need to improve their ability to answer follow-up questions accurately, especially when the conversation naturally evolves to different but related topics.
Not ideal if you are looking for a pre-built, ready-to-deploy conversational AI product rather than a research dataset and code for developing such systems.
Stars
56
Forks
6
Language
Python
License
—
Category
Last pushed
Nov 15, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/McGill-NLP/topiocqa"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
vinhkhuc/MemN2N-babi-python
End-To-End Memory Networks for bAbI question-answering tasks
patil-suraj/question_generation
Neural question generation using transformers
nelson-liu/paraphrase-id-tensorflow
Various models and code (Manhattan LSTM, Siamese LSTM + Matching Layer, BiMPM) for the...
YuriyGuts/kaggle-quora-question-pairs
My solution to Kaggle Quora Question Pairs competition (Top 2%, Private LB log loss 0.13497).
dtrizna/slp
Shell Language Processing (SLP). Pre-processing of sh/bash/zsh/.. commands for Machine Learning models.