monologg/JointBERT
Pytorch implementation of JointBERT: "BERT for Joint Intent Classification and Slot Filling"
This project helps build better virtual assistants or chatbots by accurately understanding user requests. It takes a user's typed sentence and simultaneously identifies the overall intention (like 'book a flight') and extracts key pieces of information (like 'tomorrow' for a date or 'London' for a destination). This is ideal for product managers or conversational AI designers looking to improve their system's natural language understanding.
738 stars. No commits in the last 6 months.
Use this if you need to precisely understand both what a user wants to do and the specific details they mention in a single conversational turn.
Not ideal if your primary need is for general text summarization, sentiment analysis, or document classification rather than interactive command processing.
Stars
738
Forks
199
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/monologg/JointBERT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
Tongjilibo/bert4torch
An elegent pytorch implement of transformers
nyu-mll/jiant
jiant is an nlp toolkit
lonePatient/TorchBlocks
A PyTorch-based toolkit for natural language processing
grammarly/gector
Official implementation of the papers "GECToR – Grammatical Error Correction: Tag, Not Rewrite"...
appvision-ai/fast-bert
Super easy library for BERT based NLP models