hellohaptik/HINT3

This repository contains datasets and code for the paper "HINT3: Raising the bar for Intent Detection in the Wild" accepted at EMNLP-2020's Insights Workshop https://insights-workshop.github.io/ Preprint for the paper is available here https://arxiv.org/abs/2009.13833

39
/ 100
Emerging

This project helps conversational AI developers and researchers evaluate how well different Natural Language Understanding (NLU) platforms identify user intent in real-world chatbot conversations. It provides datasets from live chatbots and allows you to compare the performance of platforms like Rasa, Dialogflow, LUIS, Haptik, and BERT-based classifiers. The primary users are NLU engineers, data scientists, and AI researchers working on chatbot development.

No commits in the last 6 months.

Use this if you need to benchmark the accuracy of various NLU platforms in identifying user intent from real user queries in diverse chatbot domains.

Not ideal if you're looking for a pre-built chatbot or a tool to deploy an NLU model directly into a production environment.

chatbot-development natural-language-understanding intent-detection conversational-ai nlu-benchmarking
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

32

Forks

7

Language

Jupyter Notebook

License

Last pushed

Mar 24, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/hellohaptik/HINT3"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.