ParlAI Projects

Here we list projects undertaken in the ParlAI framework that are shared publicly, either in the form of papers, public tasks (with leaderboards) and/or shared model code.

This directory also contains subfolders for some of the projects which are housed in the ParlAI repo, others are maintained via external websites. Please also refer to ParlAI's agents, tasks and model zoo for what else is in ParlAI.

Generative Models

• What makes a good conversation? How controllable attributes affect human judgments [paper]. Optimizing for multi-turn engaging conversations -- by controlling question-asking, specificity, response-relatedness and repetition.

• Retrieve and Refine [paper]. Models for improved chitchat ability by combining retrieval with generative refinement.

• Importance of Search Strategy [paper]. Analysis of the performance of search in generative models for chitchat tasks.

Interactive Learning

• Self-Feeding Chatbot [paper] How an agent can learn from dialogue after deployment by imitating and asking for feedback.

Chit-chat

• Dialogue Natural Language Inference [website]. Task and method for improving dialogue consistency.

• ConvAI2 Competition [website]. Competition on dialogue chitchat based on the PersonaChat task.

• Persona-Chat [project]. Task & models for chitchat with a given persona.

Knowledge Grounded

• Wizard of Wikipedia [website] [paper]. Knowledge-grounded open domain chitchat task & models.

Visually Grounded

• Image Chat [paper] [task]. Task for personality-based engaging dialogue on images.

• Personality-Captions [website] [paper]. Task for personality-based engaging comments on images.

Environment Grounded

• LIGHT [website] A large-scale text adventure game research platform for agents that speak and act.

• Mastering the Dungeon [project]. Task & models for training grounded agents in a text adventure game via MTurk.

• Talk The Walk [paper]. Task & models for grounded dialogue for the task of navigating New York City streets.

QA

• HotPotQA [external website]. QA task with multi-hop reasoning. Task built with ParlAI Mturk.

• CoQA [external website]. QA task with a series of interconnected questions. Task built with ParlAI Mturk.

• DrQA [parlai agent] [project] [external website] [paper]. QA model for answering questions by retrieving and reading knowledge.