Introduction

Recent advancements in large-scale language models like ChatGPT have expanded the horizons of natural language processing. These models excel at understanding complex language patterns and incorporating extensive knowledge. However, they have limitations such as struggling with rare information, generating incorrect content, and lacking access to real-time data due to fixed parameters. To address these issues, knowledge-augmented NLP methods have emerged. These methods offer a plug-and-play approach to enhance model performance by explicitly integrating external knowledge inputs. This bridges the gap between statistical learning from text patterns and comprehensive world knowledge. In essence, while large language models have made significant progress, their limitations make it crucial to integrate external knowledge. Knowledge-augmented NLP methods offer a promising solution, improving efficiency and effectiveness in language processing by empowering models to understand and utilize diverse knowledge inputs.

Workshop History

  • The first workshop on knowledge-augmented methods for NLP was held at AAAI 2023, attracting an enthusiastic audience of over 70 participants. The event featured four keynote speakers from both academia and industry: Dr. Scott Wen-tau Yih from FAIR, Prof. Amit Sheth from the University of South Carolina, Prof. Jordan Boyd-Graber from the University of Maryland, and Prof. Chandan Reddy from Virginia Tech. With 35 submissions from 50 institutions, the workshop accepted 26 papers spanning topics such as retrieval, knowledge graphs, commonsense augmented models, knowledge-enhanced language model pre-training, new benchmark datasets, and survey papers.

  • The second workshop on knowledge-augmented methods for NLP hosted during KDD 2023, saw a significant increase in attendance, with more than 200 in-person attendees. This time, we welcomed four keynote speakers, three of whom are leading figures in the industry: Prof. Jiawei Han from UIUC, Dr. Xin Dong from Meta AI, Dr. Francesco Barbieri from Snap, and Dr. Bing Yin from Amazon. Their discussions on the real-world applications and products powered by knowledge-augmented methods highlighted the workshop's impact. These achievements underscore our commitment to advancing the field of community, and we eagerly anticipate further enriching the community at ACL 2024.

    • Important Dates

    All deadlines are 11:59pm UTC -12h ("anywhere on Earth")

    Paper Submission Deadline

    May 17, 2024

    Notification of Acceptance

    June 17, 2024

    Camera-ready deadline

    July 1, 2024

    Workshop Date

    August 16, 2024

    Follow us on Twitter! @knowledgenlp