paper-with-me

Papers

Wizard of Wikipedia: Knowledge-Powered Conversational agents

2018-11-03 · ICLR 2019 5 · Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, Jason Weston

In open-domain dialogue intelligent agents should exhibit the use of knowledge, however there are few convincing demonstrations of this to date. The most popular sequence to sequence models typically "generate and hope" generic utterances that can be memorized in the weights of the model when mapping from input utterance(s) to output, rather than employing recalled knowledge as context. Use of knowledge has so far proved difficult, in part because of the lack of a supervised learning benchmark task which exhibits knowledgeable open dialogue with clear grounding. To that end we collect and release a large dataset with conversations directly grounded with knowledge retrieved from Wikipedia. We then design architectures capable of retrieving knowledge, reading and conditioning on it, and finally generating natural responses. Our best performing dialogue models are able to conduct knowledgeable discussions on open-domain topics as evaluated by automatic metrics and human evaluations, while our new benchmark allows for measuring further improvements in this important research direction.

📄 PDF Abstract BibTeX arXiv:1811.01241

Code (3)

facebookresearch/ParlAI/tree/master/projects/wizard_of_wikipedia
informagi/conversational-entity-linking-2022 pytorch
mangopy/direct-rag-learning pytorch

Tasks

Dialogue Generation

Similar Papers 제목 키워드 기반

Why and When: Understanding System Initiative during Conversational Collaborative Search

2023-03-23 · Sandeep Avula, Bogeum Choi, Jaime Arguello

In the last decade, conversational search has attracted considerable attention. However, most research has focused on systems that can support a \emph{single} searcher. In this paper, we explore how systems can support \…

Conversational Search

Contrastive Learning Reduces Hallucination in Conversations

2022-12-20 · Weiwei Sun, Zhengliang Shi, Shen Gao, Pengjie Ren 외

Pre-trained language models (LMs) store knowledge in their parameters and can generate informative responses when used in conversational systems. However, LMs suffer from the problem of "hallucination:" they may generate…

Contrastive LearningHallucination

Wizard of Tasks: A Novel Conversational Dataset for Solving Real-World Tasks in Conversational Settings

2022-10-01 · COLING 2022 10 · Jason Ingyu Choi, Saar Kuzi, Nikhita Vedula, Jie Zhao 외

Conversational Task Assistants (CTAs) are conversational agents whose goal is to help humans perform real-world tasks. CTAs can help in exploring available tasks, answering task-specific questions and guiding users throu…

abstractive question answeringArticlesintent-classificationIntent Classification+1

Extending Neural Generative Conversational Model using External Knowledge Sources

2018-09-14 · EMNLP 2018 10 · Prasanna Parthasarathi, Joelle Pineau

The use of connectionist approaches in conversational agents has been progressing rapidly due to the availability of large corpora. However current generative dialogue models often lack coherence and are content poor. Th…

Information Seeking in the Spirit of Learning: a Dataset for Conversational Curiosity

2020-05-01 · EMNLP 2020 11 · Pedro Rodriguez, Paul Crook, Seungwhan Moon, Zhiguang Wang

Open-ended human learning and information-seeking are increasingly mediated by digital assistants. However, such systems often ignore the user's pre-existing knowledge. Assuming a correlation between engagement and user …