Knowledge Graphs Building and Training: Engineering Aspects
This blog post will peel back the layers of our KG building and learning platform, illuminating its role in enriching machine learning. As we explore our distinctive pipelines and delve into the granularities of data provenance and GNN training, we’ll showcase how our system facilitates the seamless integration of KGs into practical, real-world tasks for production use cases.
Wrapping up 2023: Acknowledgements & Aspirations
We’d like to reflect on our collaborations and accomplishments as we wrap up the year. We put a lot of effort into our research papers and blog articles, and we’d like to thank you, the readers, for engaging with us. We also thank our guest speakers who have come into our office, virtually or in person, to share their work and dedication with us
Measuring and Modifying Factual Knowledge in Large Language Models
We introduced new metrics to measure factual knowledge in LLMs, addressing the limitations of existing ranking-based methods. Our metrics outperformed traditional ranking-based approaches, providing more accurate assessments of LLMs’ factual knowledge. We also explored the difference between implicit and explicit knowledge instillation in LLMs, highlighting that explicit knowledge instillation alone is insufficient in cases related to location and language queries.
Knowledge Graphs Are Not Created Equal: Exploring the Properties and Structure of Real KGs
We measured and analyzed various KG properties and described common/distinct structural patterns we observed in the datasets. Based on our findings, we formulated several recommendations for practitioners for future KG model development, evaluation, and dataset construction.
The First Workshop on Natural Language Processing for Human Resources
We invite scholars, researchers, and practitioners to contribute their expertise and insights to the inaugural NLP4HR workshop. We are excitedly anticipating an eclectic mix of submissions covering a broad range of HR-related topics.
Zero-Shot Triplet Extraction via Template Infilling
Our experiments show ZETT advances state-of-the-art extraction accuracy while providing a conceptually simple and stable solution. Going forward, we believe methods like ZETT that leverage self-supervised pre-training will play a key role in adapting information extraction to open-domain settings.
Megagon Team Feature: Chen Shen
Get to know Chen Shen, Senior Research Engineer at Megagon Labs as he uncovers up and coming engineering and research methods in AI and the dynamics of the Megagon office.
Megagon Labs Summer 2023 Internship Experience
In this exclusive piece, we bring you a deep dive into the most exciting projects and trends that emerged from the Summer 2023 internship program.
ACL 2023 Paper Picks
This article is meant to provide an overview of ACL 2023 with a focus on papers highlighting recent exciting breakthroughs such as large language models (LLMs). We briefly capture the papers that stood out to our attending research scientists and research engineers.
ACL 2023 Conference Highlights
A recap of ACL2023! In this post, we briefly capture the themes of the keynote talks, summarize panel discussions focusing on NLP in the era of LLMs. We also share our experience and insights from the MATCHING workshop.
