asappresearch/dialog-intent-induction
Code and data for paper "Dialog Intent Induction with Deep Multi-View Clustering", Hugh Perkins and Yi Yang, 2019, EMNLP 2019
This project helps customer service managers automatically find new, complex customer service issues directly from conversation transcripts. It takes raw dialog data, like customer support chats or call transcripts, and groups similar conversations together based on both the customer's initial query and the support team's resolution path. The output is a set of identified 'intents' or problem types that are emerging organically, which can be used to update training or improve routing.
No commits in the last 6 months.
Use this if you need to discover new and evolving customer service issues or common conversation topics that are not predefined in your existing systems.
Not ideal if you already have well-defined, simple categories for all your dialog intents and don't need to discover new ones.
Stars
67
Forks
20
Language
Python
License
MIT
Category
Last pushed
Jul 06, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/asappresearch/dialog-intent-induction"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sz128/slot_filling_and_intent_detection_of_SLU
slot filling, intent detection, joint training, ATIS & SNIPS datasets, the Facebook’s...
yuanxiaosc/BERT-for-Sequence-Labeling-and-Text-Classification
This is the template code to use BERT for sequence lableing and text classification, in order to...
dborrelli/chat-intents
Clustering sentence embeddings to extract message intent
hellohaptik/HINT3
This repository contains datasets and code for the paper "HINT3: Raising the bar for Intent...
taishan1994/pytorch_bert_intent_classification_and_slot_filling
基于pytorch的中文意图识别和槽位填充