Skip to search formSkip to main contentSkip to account menu

Wizard of Wikipedia: Knowledge-Powered Conversational agents

The best performing dialogue models are able to conduct knowledgeable discussions on open-domain topics as evaluated by automatic metrics and human evaluations, while a new benchmark allows for measuring further improvements in this important research direction.
View PDF on arXiv (opens in a new tab)

Recipes for Building an Open-Domain Chatbot

Human evaluations show the best models outperform existing approaches in multi-turn dialogue on engagingness and humanness measurements, and the limitations of this work are discussed by analyzing failure cases of the models.
View on ACL (opens in a new tab)

OPT: Open Pre-trained Transformer Language Models

This work presents Open Pre-trained Transformers (OPT), a suite of decoder-only pre-trained transformers ranging from 125M to 175B parameters, which they aim to fully and responsibly share with interested researchers.
View PDF on arXiv (opens in a new tab)

Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring

This work develops a new transformer architecture, the Poly-encoder, that learns global rather than token level self-attention features, and shows that the models achieve state-of-the-art results on four tasks.
View Paper (opens in a new tab)

The Second Conversational Intelligence Challenge (ConvAI2)

To improve performance on multi-turn conversations with humans, future systems must go beyond single word metrics like perplexity to measure the performance across sequences of utterances (conversations)—in terms of repetition, consistency and balance of dialogue acts.
View PDF on arXiv (opens in a new tab)

Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring

This work develops a new transformer architecture, the Poly-encoder, that learns global rather than token level self-attention features and achieves state-of-the-art results on three existing tasks.
View PDF on arXiv (opens in a new tab)

Internet-Augmented Dialogue Generation

An approach that learns to generate an internet search query based on the context, and then conditions on the search results to finally generate a response, a method that can employ up-to-the-minute relevant information.
View on ACL (opens in a new tab)

Retrieval Augmentation Reduces Hallucination in Conversation

This work explores the use of neural-retrieval-in-the-loop architectures recently shown to be effective in open-domain QA for knowledge-grounded dialogue, a task that is arguably more challenging as it requires querying based on complex multi-turn dialogue context and generating conversationally coherent responses.
View PDF on arXiv (opens in a new tab)

Image-Chat: Engaging Grounded Conversations

Automatic metrics and human evaluations of engagingness show the efficacy of this approach, and state-of-the-art performance on the existing IGC task is obtained, and the best performing model is almost on par with humans on the Image-Chat test set.
View on ACL (opens in a new tab)

Can You Put it All Together: Evaluating Conversational Agents’ Ability to Blend Skills

This work investigates several ways to combine models trained towards isolated capabilities, ranging from simple model aggregation schemes that require minimal additional training, to various forms of multi-task training that encompass several skills at all training stages.
View on ACL (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)