Zhiwei Hu and Xiaoqi Han, from Shanxi University will give a talk online, for the Coffee House Tech Talk Series. Details of the talk are below.

Title: Knowledge Representation Learning and Editing

Speaker: Zhiwei Hu and Xiaoqi Han

Time: 06/27(Thur) 12:00-13:00 (UTC+01:00)London

Location: 4th floor Bayes Centre

Registration: https://www.smartsurvey.co.uk/s/D8MKWE/

External: https://app.huawei.com/wmeeting/join/96307512/mC4On8yRPIEEyULYircEDacM7osV3CodS

Meeting ID: 96307512

Passcode: 407435

Abstract:

Knowledge Representation Learning (KRL) focus on capture the semantic information between entities and relations from the real word knowledge, which is useful for various AI tasks such as reasoning, recommendation, and prediction. One of the main challenges in KRL is capturing the complexity and diversity of real-world knowledge, especially effectively integrating different types of information, such as type and hyper-relational content. Another challenge of knowledge representataion in LLM is how to correct mistakes in LLMs’ representation without resorting to exhaustive retraining or continuous training procedures. In this presentation, on the one hand, we focus on how to better encode the schema content of entities and relations in knowledge graphs into related tasks such as complex query answering and entity typing. On the other hand, we seek to present a systematic and current overview of cutting-edge methods, and provide insights into real-world applications and engage in discussions about future research directions.

【BAYES COFFEE HOUSE TECH TALK SERIES】Knowledge Representation Learning and Editing / Huawei-Edinburgh Joint Lab by blogadmin is licensed under a Creative Commons Attribution CC BY 3.0