I have been working with LangChain applications for quite a while now and as you might know there is always something new to learn in the GenAI universe. So a couple of weeks ago I was going through…
TLDR — Extractive question answering is an important task for providing a good user experience in many applications. The popular Retriever-Reader framework for QA using BERT can be difficult to scale…
As data scientists, we spend a lot of our time doing exploratory data analysis (EDA), cleaning data and making sure the data we use to generate insights is of good quality. Have you ever found…
This talk explores the integration of Knowledge Graphs (KGs) and Large Language Models (LLM) to harness their combined power for improved natural language understanding. By leveraging KGs' structured knowledge and language models' text comprehension abilities, we can leverage the domain-specific–and potentially sensitive–data together with the general knowledge of LLMs.
We also examine how language models can enhance KGs through knowledge extraction and refinement. The integration of these technologies presents opportunities in various domains, from question-answering to chatbots, fostering more intelligent and context-aware applications.
C. Tahri, X. Tannier, and P. Haouat. Proceedings of the first Workshop on Information Extraction from Scientific Publications, page 67--77. Online, Association for Computational Linguistics, (November 2022)
M. Windl, V. Winterhalter, A. Schmidt, and S. Mayer. Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, New York, NY, USA, Association for Computing Machinery, (2023)