WING-NUS / Sequicity
Source code for the ACL 2018 paper entitled "Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures" by Wenqiang Lei et al.
Stars: ✭ 145
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Sequicity
Cdial Gpt
A Large-scale Chinese Short-Text Conversation Dataset and Chinese pre-training dialog models
Stars: ✭ 596 (+311.03%)
Mutual labels: dialogue
C3
Investigating Prior Knowledge for Challenging Chinese Machine Reading Comprehension
Stars: ✭ 101 (-30.34%)
Mutual labels: dialogue
Nlp Paper
自然语言处理领域下的对话语音领域,整理相关论文(附阅读笔记),复现模型以及数据处理等(代码含TensorFlow和PyTorch两版本)
Stars: ✭ 67 (-53.79%)
Mutual labels: dialogue
Som Dst
SOM-DST: Efficient Dialogue State Tracking by Selectively Overwriting Memory (ACL 2020)
Stars: ✭ 79 (-45.52%)
Mutual labels: dialogue
Dialogic
💬 Create dialogs, characters and scenes to display conversations in your Godot games.
Stars: ✭ 414 (+185.52%)
Mutual labels: dialogue
Geneva
Code to train and evaluate the GeNeVA-GAN model for the GeNeVA task proposed in our ICCV 2019 paper "Tell, Draw, and Repeat: Generating and modifying images based on continual linguistic instruction"
Stars: ✭ 71 (-51.03%)
Mutual labels: dialogue
Nlp Library
curated collection of papers for the nlp practitioner 📖👩🔬
Stars: ✭ 1,025 (+606.9%)
Mutual labels: dialogue
Dream
DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension
Stars: ✭ 60 (-58.62%)
Mutual labels: dialogue
Msr Nlp Projects
This is a list of open-source projects at Microsoft Research NLP Group
Stars: ✭ 92 (-36.55%)
Mutual labels: dialogue
Nlg Eval
Evaluation code for various unsupervised automated metrics for Natural Language Generation.
Stars: ✭ 822 (+466.9%)
Mutual labels: dialogue
Scribble
Efficient multi-effects text renderer for GameMaker Studio 2.3.1
Stars: ✭ 123 (-15.17%)
Mutual labels: dialogue
Rnnlg
RNNLG is an open source benchmark toolkit for Natural Language Generation (NLG) in spoken dialogue system application domains. It is released by Tsung-Hsien (Shawn) Wen from Cambridge Dialogue Systems Group under Apache License 2.0.
Stars: ✭ 487 (+235.86%)
Mutual labels: dialogue
Dialogue Understanding
This repository contains PyTorch implementation for the baseline models from the paper Utterance-level Dialogue Understanding: An Empirical Study
Stars: ✭ 77 (-46.9%)
Mutual labels: dialogue
Dstc7 End To End Conversation Modeling
Grounded conversational dataset for end-to-end conversational AI (official DSTC7 data)
Stars: ✭ 141 (-2.76%)
Mutual labels: dialogue
Self dialogue corpus
The Self-dialogue Corpus - a collection of self-dialogues across music, movies and sports
Stars: ✭ 98 (-32.41%)
Mutual labels: dialogue
Sequicity
Source code for the ACL 2018 paper entitled "Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures" by Wenqiang Lei et al.
@inproceedings{lei2018sequicity,
title={Sequicity: Simplifying task-oriented dialogue systems with single sequence-to-sequence architectures},
author={Lei, Wenqiang and Jin, Xisen and Kan, Min-Yen and Ren, Zhaochun and He, Xiangnan and Yin, Dawei},
booktitle={ACL},
year={2018}
}
Training with default parameters
python model.py -mode train -model [tsdf-camrest|tsdf-kvret]
(optional: configuring hyperparameters with cmdline)
python model.py -mode train -model [tsdf-camrest|tsdf-kvret] -cfg lr=0.003 batch_size=32
Testing
python model.py -mode test -model [tsdf-camrest|tsdf-kvret]
Reinforcement fine-tuning
python model.py -mode rl -model [tsdf-camrest|tsdf-kvret] -cfg lr=0.0001
Before running
- Install required python packages. We used pytorch 0.3.0 and python 3.6 under Linux operating system.
pip install -r requirements.txt
- Make directories under PROJECT_ROOT.
mkdir vocab
mkdir log
mkdir results
mkdir models
mkdir sheets
- Download pretrained Glove word vectors and place them in PROJECT_ROOT/data/glove.
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].