ParlAI (pronounced “par-lay”) is a python framework for sharing, training and testing dialogue models, from open-domain chitchat, to task-oriented dialogue, to visual question answering.
Its goal is to provide researchers:
- 100+ popular datasets available all in one place, with the same API, among them PersonaChat, DailyDialog, Wizard of Wikipedia, Empathetic Dialogues, SQuAD, MS MARCO, QuAC, HotpotQA, QACNN & QADailyMail, CBT, BookTest, bAbI Dialogue tasks, Ubuntu Dialogue, OpenSubtitles, Image Chat, VQA, VisDial and CLEVR. See the complete list here.
- a wide set of reference models -- from retrieval baselines to Transformers.
- a large zoo of pretrained models ready to use off-the-shelf
- seamless integration of Amazon Mechanical Turk for data collection and human evaluation
- integration with Facebook Messenger to connect agents with humans in a chat interface
- a large range of helpers to create your own agents and train on several tasks with multitasking
- multimodality, some tasks use text and images
ParlAI is described in the following paper: “ParlAI: A Dialog Research Software Platform", arXiv:1705.06476 or see these more up-to-date slides.
Follow us on Twitter and check out our Release notes to see the latest information about new features & updates, and the website http://parl.ai for further docs. For an archived list of updates, check out NEWS.md.
Interactive Tutorial
For those who want to start with ParlAI now, you can try our Colab Tutorial.
Installing ParlAI
ParlAI currently requires Python3.7+ and Pytorch 1.6 or higher. Dependencies of the core modules are listed in requirements.txt. Some models included (in parlai/agents) have additional requirements. We strongly recommend you install ParlAI in a venv or conda environment.
Standard Installation
If you want to use ParlAI without modifications, you can install it with:
pip install parlai
Development Installation
Many users will want to modify some parts of ParlAI. To set up a development environment, run the following commands to clone the repository and install ParlAI:
git clone https://github.com/facebookresearch/ParlAI.git ~/ParlAI
cd ~/ParlAI; python setup.py develop
All needed data will be downloaded to ~/ParlAI/data. If you need to clear out the space used by these files, you can safely delete these directories and any files needed will be downloaded again.
Documentation
- Quick Start
- Basics: world, agents, teachers, action and observations
- Creating a new dataset/task
- List of available tasks/datasets
- Creating a seq2seq agent
- List of available agents
- Model zoo (list pretrained models)
- Running crowdsourcing tasks
- Plug into Facebook Messenger
Examples
A large set of scripts can be found in parlai/scripts. Here are a few of them. Note: If any of these examples fail, check the installation section to see if you have missed something.
Display 10 random examples from the SQuAD task
parlai display_data -t squad
Evaluate an IR baseline model on the validation set of the Personachat task:
parlai eval_model -m ir_baseline -t personachat -dt valid
Train a single layer transformer on PersonaChat (requires pytorch and torchtext). Detail: embedding size 300, 4 attention heads, 2 epochs using batchsize 64, word vectors are initialized with fasttext and the other elements of the batch are used as negative during training.
parlai train_model -t personachat -m transformer/ranker -mf /tmp/model_tr6 --n-layers 1 --embedding-size 300 --ffn-size 600 --n-heads 4 --num-epochs 2 -veps 0.25 -bs 64 -lr 0.001 --dropout 0.1 --embedding-type fasttext_cc --candidates batch
Code Organization
The code is set up into several main directories:
- core: contains the primary code for the framework
- agents: contains agents which can interact with the different tasks (e.g. machine learning models)
- scripts: contains a number of useful scripts, like training, evaluating, interactive chatting, ...
- tasks: contains code for the different tasks available from within ParlAI
- mturk: contains code for setting up Mechanical Turk, as well as sample MTurk tasks
- messenger: contains code for interfacing with Facebook Messenger
- utils: contains a wide number of frequently used utility methods
- crowdsourcing: contains code for running crowdsourcing tasks, such as on Amazon Mechanical Turk
- chat_service: contains code for interfacing with services such as Facebook Messenger
- zoo: contains code to directly download and use pretrained models from our model zoo
Support
If you have any questions, bug reports or feature requests, please don't hesitate to post on our Github Issues page. You may also be interested in checking out our FAQ and our Tips n Tricks.
Please remember to follow our Code of Conduct.
Contributing
We welcome PRs from the community!
You can find information about contributing to ParlAI in our Contributing document.
The Team
ParlAI is currently maintained by Moya Chen, Emily Dinan, Dexter Ju, Mojtaba Komeili, Spencer Poff, Pratik Ringshia, Stephen Roller, Kurt Shuster, Eric Michael Smith, Megan Ung, Jack Urbanek, Jason Weston, Mary Williamson, and Jing Xu. Stephen Roller is the current Tech Lead.
Former major contributors and maintainers include Alexander H. Miller, Margaret Li, Will Feng, Adam Fisch, Jiasen Lu, Antoine Bordes, Devi Parikh, Dhruv Batra, Filipe de Avila Belbute Peres, Chao Pan, and Vedant Puri.
Citation
Please cite the arXiv paper if you use ParlAI in your work:
@article{miller2017parlai,
title={ParlAI: A Dialog Research Software Platform},
author={{Miller}, A.~H. and {Feng}, W. and {Fisch}, A. and {Lu}, J. and {Batra}, D. and {Bordes}, A. and {Parikh}, D. and {Weston}, J.},
journal={arXiv preprint arXiv:{1705.06476}},
year={2017}
}
License
ParlAI is MIT licensed. See the LICENSE file for details.
15.3k Dec 30, 2022
13 Sep 8, 2022
216 Dec 22, 2022
2 Nov 5, 2021
132 Nov 25, 2022
20 Jul 11, 2022
5 Jul 17, 2022
90 Dec 27, 2022
14 Aug 24, 2022
914 Jan 7, 2023
48 Jan 2, 2023
89 Nov 10, 2022
129 Jan 6, 2023
197 Dec 25, 2022
681 Jan 1, 2023
730 Jan 9, 2023
29 Oct 23, 2022