All Projects → friday27 → Slotfilling

friday27 / Slotfilling

Licence: other
Using Tensorflow to train a slot-filling & intent joint model

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Slotfilling

Deeppavlov
An open source library for deep learning end-to-end dialog systems and chatbots.
Stars: ✭ 5,525 (+39364.29%)
Mutual labels:  slot-filling, intent-classification
Snips Nlu
Snips Python library to extract meaning from text
Stars: ✭ 3,583 (+25492.86%)
Mutual labels:  slot-filling, intent-classification
OpenUE
OpenUE是一个轻量级知识图谱抽取工具 (An Open Toolkit for Universal Extraction from Text published at EMNLP2020: https://aclanthology.org/2020.emnlp-demos.1.pdf)
Stars: ✭ 274 (+1857.14%)
Mutual labels:  slot-filling, intent-classification
utterance parser
Extract intent and entities from natural language utterances
Stars: ✭ 34 (+142.86%)
Mutual labels:  slot-filling
chatbot
🤖️ 基于 PyTorch 的任务型聊天机器人(支持私有部署和 docker 部署的 Chatbot)
Stars: ✭ 77 (+450%)
Mutual labels:  slot-filling
slotminer
Tool for slot extraction from text
Stars: ✭ 15 (+7.14%)
Mutual labels:  slot-filling
JointIDSF
BERT-based joint intent detection and slot filling with intent-slot attention mechanism (INTERSPEECH 2021)
Stars: ✭ 55 (+292.86%)
Mutual labels:  slot-filling
Few-Shot-Intent-Detection
Few-Shot-Intent-Detection includes popular challenging intent detection datasets with/without OOS queries and state-of-the-art baselines and results.
Stars: ✭ 63 (+350%)
Mutual labels:  intent-classification
nlcli
Natural language interface for the command line.
Stars: ✭ 21 (+50%)
Mutual labels:  intent-classification
alter-nlu
Natural language understanding library for chatbots with intent recognition and entity extraction.
Stars: ✭ 45 (+221.43%)
Mutual labels:  intent-classification
CMID
Chinese Medical Intent Dataset
Stars: ✭ 92 (+557.14%)
Mutual labels:  intent-classification
# Slotfilling
Using Tensorflow to train a slot-filling & intent joint model


Prerequisites:
gensim
tensorflow
numpy
pandas


0. Create a folder named "ckpt"

1. Download raw data from wiki: https://dumps.wikimedia.org/backup-index.html

2. word2vec/wiki_to_txt.py
    python3 wiki_to_txt.py zhwiki-201xxxxx-pages-articles.xml.bz2
    (generated file: wiki_texts_en.txt)
    
3. word2vec/word2vec_train.py
    (generated file: en.model.bin)
    
4. model/dict.py
    - It will generate 2 csv files with intents, labels and their indexes
    
5. model/model_train.py

6. model/inference.py
    - edit line 9-10 to the checkpoint file you just trained


Ref:
[Training Word2Vec Model on English Wikipedia by Gensim]
http://textminingonline.com/training-word2vec-model-on-english-wikipedia-by-gensim

[以 gensim 訓練中文詞向量]
http://zake7749.github.io/2016/08/28/word2vec-with-gensim/
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].