zliucr/coach
Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling (ACL-2020)
This project helps build conversational AI systems that can understand user requests across different topics, even with limited training data for a new topic. It takes spoken or written user utterances as input and identifies key pieces of information (slots) within them, like a song title or a destination. This is useful for product managers or AI trainers creating chatbots, voice assistants, or other task-oriented dialogue systems.
No commits in the last 6 months.
Use this if you need to rapidly expand an existing dialogue system to support new domains or intents without collecting vast amounts of new training data.
Not ideal if you are looking for a pre-trained, ready-to-deploy conversational AI solution without any customization or development work.
Stars
77
Forks
19
Language
Python
License
MIT
Category
Last pushed
Nov 12, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/zliucr/coach"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
codertimo/BERT-pytorch
Google AI 2018 BERT pytorch implementation
JayYip/m3tl
BERT for Multitask Learning
920232796/bert_seq2seq
pytorch实现 Bert 做seq2seq任务，使用unilm方案,现在也可以做自动摘要，文本分类，情感分析，NER，词性标注等任务,支持t5模型，支持GPT2进行文章续写。
sileod/tasknet
Easy modernBERT fine-tuning and multi-task learning
graykode/toeicbert
TOEIC(Test of English for International Communication) solving using pytorch-pretrained-BERT model.