NewsDialogues: Towards Proactive News Grounded Conversation logo

NewsDialogues: Towards Proactive News Grounded Conversation

In this paper, we propose a novel task, Proactive News Grounded Conversation, in which a dialogue system can proactively lead the conversation based on some key topics of the news.

GitHub Link

The GitHub link is https://github.com/sihengli99/newsdialogues

Introduce

The GitHub repository "NewsDialogues" presents the dataset and code for the ACL'2023 Findings paper on "NewsDialogues Towards Proactive News Grounded Conversation." The dataset contains conversation data stored in the 'dataset' folder, featuring train, valid, and test files used in experiments. Each conversation entry includes grounded news articles, article titles, dates, URLs, human-annotated key topics, and dialogues. Dialogues comprise user and agent utterances, along with dialog acts, target topics, knowledge spans, and indicators for unanswerable questions. In this paper, we propose a novel task, Proactive News Grounded Conversation, in which a dialogue system can proactively lead the conversation based on some key topics of the news.

Content

ACL'2023 (Findings): NewsDialogues: Towards Proactive News Grounded Conversation...

Alternatives & Similar Tools

LongLLaMA-handle very long text contexts, up to 256,000 tokens logo

LongLLaMA is a large language model designed to handle very long text contexts, up to 256,000 tokens. It's based on OpenLLaMA and uses a technique called Focused Transformer (FoT) for training. The repository provides a smaller 3B version of LongLLaMA for free use. It can also be used as a replacement for LLaMA models with shorter contexts.