Australian National University

Wenyi Pi

Neo4j APOC Library Use Case

 Author

Wenyi Pi (

 ORCID:

0009–0002–2884–277)

 Introduction

In the realm of Neo4j, the APOC (Awesome Procedures on Cypher) library stands as a powerful tool. Previously, We have talked about the importance of APOC in optimising Cypher queries and improving query efficiency in our article Exploring Methods of Cypher Query Optimisations.

Introduction to APOC: Enhancing Neo4j Capabilities

Xuzeng He

Latest findings in multiple research directions for handling graph prediction and optimization Author · Xuzeng He (

 ORCID:

0009–0005–7317–7426) A graph, in short, is a description of items linked by relations, where the items of a graph are called

 nodes

(or vertices) and their relations are called

 edges

(or links). Examples of graphs can include social networks (e.g. Instagram) or knowledge

Recent Advances in using Machine Learning with Graphs

Vaibhav Khobragade

Author: Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982) Introduction Large language models (LLMs) are becoming increasingly popular in natural language processing for their superior competence in various applications.

Enhancing Language Models: The Role of Knowledge Graph Augmentation in Overcoming LLM Challenges

Enhancing Data Interactivity with LLMs and Neo4j Knowledge Graphs Author Wenyi Pi (

 ORCID

: 0009–0002–2884–2771) Introduction Since OpenAI launched ChatGPT, a

 large language model (LLM)

based chatbot, in 2023, it has set off a technological wave.

The integration of large language models (LLMs) with Neo4j-based knowledge graphs

An Introduction to RA-CM3, MuRAG and RACE Author  Xuzeng He (ORCID: 0009-0005-7317-7426)  Generative Artificial Intelligence (GAI) has demonstrated impressive performances in tasks such as text generation and text-to-image generation.

Recent Advances in using Retrieving Multimodal Information for Augmented Generation

Amanda Kau

Unlocking the Power of Questions — A deep dive into Question Answering Systems

Author:

 Amanda Kau (ORCID:


 0009–0004–4949–9284


 )

Virtual assistants have popped up on numerous websites over the years.

Harnessing The Power of Knowledge Graphs in Question Answering

Qingqin Fang

An Introduction to Retrieval Augmented Generation (RAG) and Knowledge Graph

Author Qingqin Fang (ORCID: 0009–0003–5348–4264)

 Introduction

Large Language Models (LLMs) have transformed the landscape of natural language processing, demonstrating exceptional proficiency in generating text that closely resembles human language.

Hallucination in Large Language Models and Two Effective Alleviation Pathways

Yunzhong Zhang

Efficient creation of a stoplight report with data dashboard images

Author: Yunzhong Zhang (ORCID: 0009–0002–8177–419X) Comparing data dashboards is crucial for understanding trends and performance differences. Traditionally, this task required manual effort, which was slow and sometimes inaccurate. Now, thanks to OpenAI’s GPT-4 with Vision (GPT-4V), we are able to automate and improve this process.

How to use GPT-4V For Stoplight Report

Dhruv Gupta

Improving the performance of Large Language Models Author  Dhruv Gupta (ORCID: 0009-0004-7109-5403)  ChatGPT, which first came out in late 2022, took the world by storm. Since then, various LLM models and LLM based products such as Meta’s Llama and Google’s Gemini have emerged, demonstrating the power of LLMs.

RAG: The next big thing after LLMs?

Harvesting the Power and Knowledge of Large Language Models


 Author

Amanda Kau

 (ORCID:

0009–0004–4949–9284

 )

Introduction Knowledge Graphs are networks that represent data in a graphical format. The beauty of Knowledge Graphs lies in their representation of concepts, events and entities as nodes, and the relationships between them as edges.

Automated Knowledge Graph Construction with Large Language Models

Swinburne University of Technology

Nakul Nambiar

Zhuochen Wu

Authors:  Nakul Nambiar (ORCID: 0009-0009-9720-9233) Zhuochen Wu (ORCID: 0009-0000-5642-5348)  Research Graph is a structured representation of research objects that captures information about entities and the relationships between Researcher, Organisation, Publication, Grant and Research Data.

How to use GPT API to export a research graph from PDF publications

Dhruv Gupta

Prompt Engineering — Part 2


 Using intelligence to use artificial Intelligence: A deep dive into Prompt Engineering

Author Dhruv Gupta

 (ORCID:

0009–0004–7109–5403

 )

Introduction In the previous article we discussed what prompt engineering and some of the techniques used for prompt engineering.

Prompt Engineering — Part 2

Enhancing Open-Domain Conversational Question Answering with Knowledge-Enhanced Models and Knowledge Graphs


 How knowledge-enhanced language models and knowledge graphs are advancing open-domain conversational question answering

Author:

 Wenyi Pi (ORCID:


 0009-0002-2884-2771


 )

When searching for information on the website, it is common to come across a flood of

Enhancing Open-Domain Conversational Question Answering with Knowledge-Enhanced Models and…

Recent Advances in Using Machine Learning with Graphs — Part 2 Latest findings in multiple research directions for handling graph construction and network security issues Author · Xuzeng He (

 ORCID:

0009–0005–7317–7426) Introduction A graph, in short, is a description of items linked by relations, where the items of a graph are called nodes (or vertices) and their relations are called edges (or links). Examples of

Recent Advances in Using Machine Learning with Graphs — Part 2

Exploring AI’s Ethical Terrain: Addressing Bias, Security, and Beyond

Author: Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982) Large language models (LLMs) like OpenAI’s GPT-4, Meta’s LLaMA, and Google Gemini (previously called Bard) have showcased their vast capabilities, from passing bar exams and crafting articles to generating images and website code.

Ethics and AI: Confronting the Challenges Ahead

How to efficiently retrieve information for different applications

Author Wenyi Pi (ORCID: 0009-0002-2884-2771) This article aims to explore various ways in which Retrieval-Augmented Generation (RAG) can be utilised to retrieve information and generate responses effectively within the dialogue system. The rationale behind utilising RAG as well as potential ways in which it can be employed effectively will be covered.

Efficient Information Retrieval and Response Generation with Retrieval-Augmented Generation (RAG)

Amir Aryani

Authors  Nakul Nambiar (ORCID: 0009-0009-9720-9233) Amir Aryani (ORCID: 0000-0002-4259-9774)  Knowledge graphs, which offer a structured representation of data and its relationships, are revolutionising how we organise and access information.

Mini RAG using Neo4j

Aishwarya Nambissan

A novel approach to improving the efficiency of text search in graph databases utilizing Neo4j, OpenAI, and Typesense. Authors  Nakul Nambiar (ORCID: 0009–0009–9720–9233) Aishwarya Nambissan (ORCID: 0009–0003–3823–6609)  The ability to use cutting-edge tools and frameworks is essential for staying ahead in the ever-changing field of technology.

Typesense and Neo4j in a hybrid information retrieval solution

Amir Aryani

A brief overview of different types of clustering techniques and their algorithms. Authors Aishwarya Nambissan (ORCID: 0009-0003-3823-6609) Amir Aryani (ORCID: 0000-0002-4259-9774)

 Background

Clustering is a fascinating technique used in machine learning, where patterns or data points are grouped based on their similarities. It’s like finding hidden connections among different data points without predefined labels.

19 Clustering Techniques

Understanding the Evolutionary Journey of LLMs Author Wenyi Pi (

 ORCID

: 0009–0002–2884–2771) Introduction When we talk about large language models (LLMs), we are actually referring to a type of advanced software that can communicate in a human-like manner. These models have the amazing ability to understand complex contexts and generate content that is coherent and has a human feel.

Brief Introduction to the History of Large Language Models (LLMs)

Understanding Sequential Data Modelling with Keras for Time Series Prediction

 Author

Wenyi Pi (

 ORCID

: 0009–0002–2884–2771) Introduction Recurrent Neural Networks (RNNs) are a special type of neural networks that are suitable for learning representations of sequential data like text in Natural Language Processing (NLP). We will walk through a complete example of using RNNs for time series prediction, covering

Beginner’s Guide to Recurrent Neural Networks (RNNs) with Keras

Incorporating Knowledge Graphs to explain reasoning processes


 Author

Amanda Kau (

 ORCID:

0009–0004–4949–9284) Introduction Large language models (LLMs) like GPT-4 possess remarkable language abilities, allowing them to function as chatbots, translators, and much more.

Combining Knowledge Graphs With Language Models for Interpretability

Exploring the OpenAlex Data Structure and Visualization Author: Qingqin Fang (

 ORCID:

0009–0003–5348–4264)

 Introduction to OpenAlex

In today’s world, the realm of research papers is brimming with countless hot topics, and the sheer volume of publications can be overwhelming.

Unveiling Research Trends through OpenAlex Visualization

Large Language Models for Fake News Generation and Detection Author Amanda Kau (

 ORCID

: 0009–0004–4949–9284) Introduction In recent years, fake news has become an increasing concern for many, and for good reason. Newspapers, which we once trusted to deliver credible news through accountable journalists, are vanishing en masse along with their writers.

Are Large Language Models Our Allies or Enemies in the Fight Against Fake News?

Unlocking the power of language models: A deep dive into BERT


 Author:


 Dhruv Gupta (ORCID:


 0009–0004–7109–5403


 )

Clive Humby, in 2006 rightly said, “Data is the new oil”. With data being present everywhere, it has never been more valuable.

Language Models: Deep Dive into BERT

Attention mechanism not getting enough attention Author Dhruv Gupta (

 ORCID

: 0009–0004–7109–5403) Introduction As discussed in this article, RNNs were incapable of learning long-term dependencies. To solve this issue both LSTMs and GRUs were introduced. However, even though LSTMs and GRUs did a fairly decent job for textual data they did not perform well.

Transformers Models in NLP

Exploring the potentials and limitations of Vision Language Models

Author:

 Amanda Kau (ORCID:


 0009–0004–4949–9284


 )

The human brain is more extraordinary than any machine we could build. From an early age, many of us gain the ability to comprehend what our eyes tell us and articulate it. Furthermore, we combine evidence from all our senses to reason.

How Much Can Vision Language Models Really “See”?

A novel compression technique ensuring comparable performance with 70% less parameters

Author Amanda Kau (

 ORCID

: 0009–0004–4949–9284) Introduction The sizes of large language models (LLMs) have been steadily increasing over the last few years.

CompactifAI: Large Language Models Don’t Actually Have To Be Large

From Naive to Modular: Tracing the Evolution of Retrieval-Augmented Generation

Author · Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982) Introduction Large Language Models (LLMs) have achieved remarkable success.

Three Paradigms of RAG

An introduction to tools supporting PubMed Author: Xuzeng He (

 ORCID:

0009–0005–7317–7426) PubMed is a free Web literature search service developed and maintained by the National Center for Biotechnology Information (

 NCBI

), and it is also a part of NCBI’s Entrez retrieval system that provides access to a diverse set of 38 databases.

Enhancing PubMed: from a Medical Database to beyond

Aland Astudillo

How to use GROBID to extract text from PDF  Author  Aland Astudillo (ORCID: 0009-0008-8672-3168)  GROBID is a powerful and useful tool based on machine learning that can extract text information from PDF files and other files to a structured format. One of the key challenges in knowledge mining from academic articles is reading the content of PDF files.

How to use GROBID

Using Mistral for Data tagging Author · Xuzeng He (

 ORCID:

0009–0005–7317–7426) Introduction Data tagging, in simple terms, is the process of assigning labels or tags to your data so that they are easier to retrieve or analyse.

How to use Large Language Models to tag your data: A complete tutorial

Integrating temporal data into static knowledge graphs

 Author

Amanda Kau

 (ORCID:


 0009–0004–4949–9284


 )

Introduction Knowledge graphs (KGs) have proven to be an effective method of data representation that is increasingly popular. In KGs, entities and concepts are represented as nodes, while the relationships between nodes are depicted as edges.

Dynamic Knowledge Graphs: A Next Step For Data Representation?

Transformative Advances in Language Models through External Knowledge Integration

Author: Qingqin Fang (

 ORCID:

0009–0003–5348–4264)

 Introduction

In the dynamic field of natural language processing, the integration of external knowledge has emerged as a pivotal strategy for enhancing the performance of language models.

Deeper understanding of In-Context Retrieval-Augmented Language Models

Author  Amir Aryani (ORCID: 0000-0002-4259-9774) Introduction   In this article we look at Research Graph as an information model , and an approach to connect and capture the connections between research outputs, researchers and research activities. We explore the metadata model, and we discuss how to capture this graph in a Neo4j Graph Database.

Research Graph 101

Latest findings in multiple research directions for tackling reasoning and common sense challenges Author: Xuzeng He (

 ORCID:

0009–0005–7317–7426) Knowledge Graphs, such as Wikidata, contain rich relational information between entities and have been widely used as a structured format for storing and representing relational information.

Large Language Models and Knowledge Graphs: Ways to combine them

Using intelligence to use artificial Intelligence: A deep dive into Prompt Engineering


 Author


 Dhruv Gupta (ORCID:


 0009–0004–7109–5403


 )

Introduction Large Language Models (LLMs) have become the new normal in the field of Natural Language Processing (NLP). With their improved performance and generative power, people around the world are relying on it for

Prompt Engineering

Boosting Performance for Knowledge Graphs with Neo4j APOC Library

 Author

Wenyi Pi (ORCID: 0009–0002–2884–2771) Introduction A

 knowledge graph

(graph database) captures information about main entities in a domain and the relationships between them. It was an augmented feature store for connected data which gave access to compute, access and operationalise structure features.

Exploring Methods of Cypher Query Optimisations

The AI Helper Turning Mountains of Data into Bite-Sized Instructions

Author Aland Astudillo (ORCID: 0009-0008-8672-3168) LLMs have been changing the way the entire world deals with problems and day-by-day tasks. To make them better for specific applications, they need huge amounts of data and complex and expensive approaches to training them.

What is LLMLingua?

Refining AI Vision: How Retrieval-Augmented Generation Transforms Image Captioning in Large Language Models   Leveraging External Knowledge to Enhance the Descriptive Capabilities of AI Systems Author  Vaibhav Khobragade (ORCID: 0009–0009–8807–5982) Introduction   Large Language Models (LLMs) are artificial intelligence models that are trained on massive amounts of text data in order to generate human-like language and produce coherent

Refining AI Vision: How Retrieval-Augmented Generation Transforms Image Captioning in Large…

Tools and Platform for Integration of Knowledge Graph with RAG pipelines.

Authors Aland Astudillo (ORCID: 0009-0008-8672-3168) Aishwarya Nambissan (ORCID: 0009-0003-3823-6609) Many users of chatbots such as ChatGPT, have encountered the problem of receiving inappropriate or incompatible responses. There are several reasons why this might happen.

Unveiling the Synergy: Retrieval Augmented Generation (RAG) Meets Knowledge Graphs

Author  Amir Aryani: (ORCID: 0000-0002-4259-9774) Definition   A research collaboration network is a group of researchers, and practitioners, or both, working together on joint research activities. These networks often span across disciplines, geographic boundaries, and sectors, enabling participants to share resources, expertise, and data to address common research goals more effectively than they could individually.

Research Collaboration Network

Improving the performance and application of Large Language Models

Author Amanda Kau (ORCID: 0009-0004-4949-9284) Large language models (LLMs) like GPT-4, the engine of products like ChatGPT, have taken centre stage in recent years due to their astonishing capabilities. Yet, they are far from perfect.

Understanding Retrieval Pitfalls: Challenges Faced by Retrieval Augmented Generation (RAG) models

Exploring the Potential of Temporal Feature-Logic Embedding (TFLEX) in Complex Query Resolution

Author · Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982)

 Introduction

Artificial intelligence (AI) and knowledge representation in the field of temporal knowledge graphs are rapidly gaining interest.

Harnessing Temporal Dynamics: Advanced Reasoning using Temporal Knowledge Graphs

Exploring innovative Strategies in Combating Misinformation with Enhanced Multimodal Understanding Author Wenyi Pi (

 ORCID

: 0009–0002–2884–2771) Introduction Misinformation refers to false or inaccurate information that is often given to someone in a deliberate attempt to make them believe something that is not true. This has a significantly negative impact on public health, political stability and social trust and harmony.

Multimodal Large Language Models for Misinformation Detection and Reasoning

The Three Oldest Pillars of NLP

Author Dhruv Gupta (

 ORCID

: 0009–0004–7109–5403) Introduction Natural Language Processing (NLP) has almost become synonymous with Large Language Models (LLMs), Generative AI, and fancy chatbots. With the ever-increasing amount of textual data and exponential growth in computational knowledge, these models are improving every day.

RNNs vs GRUs vs LSTMs

A Unified and Collaborative Framework for LLM Author · Qingqin Fang (

 ORCID:

0009–0003–5348–4264) Introduction In today’s rapidly evolving field of artificial intelligence, large language models (LLMs) are demonstrating unprecedented potential. Particularly, the Retrieval-Augmented Generation (RAG) architecture has become a hot topic in AI technology due to its unique technical capabilities.

RAG 2.0 is Coming?

Bridging Human Perception and AI’s Future: The Convergence of Visual Understanding and Semantic Networks Author · Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982)

 Introduction

The fusion of Vision-Language Models (

 VLMs

), Generative Models, and Knowledge Graphs (

 KGs

) is reshaping how artificial intelligence (AI) understands and interacts with the world.

Tuning Vision-Language Models and Generative Models with Knowledge Graph

Understanding the Power and Applications of Natural Language Processing

 Author

Dhruv Gupta (

 ORCID:

0009–0004–7109–5403) Introduction We are living in the era of generative AI. In an era where you can ask AI models almost anything, they will most certainly have an answer to the query. With the increased computational power and the amount of textual data, these models are bound to improve their performance.

NLU vs. NLG: Unveiling the Two Sides of Natural Language Processing

Understanding how RNNs work and its applications


 Author

Wenyi Pi (

 ORCID

: 0009–0002–2884–2771) Introduction In the ever-evolving landscape of artificial intelligence (AI), bridging the gap between humans and machines has seen remarkable progress. Researchers and enthusiasts alike have tirelessly worked across numerous aspects of this field, bringing about amazing advancements.

An Introduction to Recurrent Neural Networks (RNNs)

Exploring the Boundaries of Creativity and Responsibility in the Age of AI-Driven Media

 Author

Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982)

 Introduction

In 2024, the discipline of Generative AI takes a big step forward with the launch of revolutionary models that convert text into dynamic films, altering the landscape of digital content creation.

Generative AI’s Leap into Video in 2024 and its Ethical Horizon

Addressing Misinformation, Bias, and Privacy Concerns

Author:

 Wenyi Pi (ORCID:


 0009–0002–2884–2771


 )

Recently, the spread of false or misinformation has become an important concern for people all over the world, especially in the era of big data and multimedia, where people are faced with a flood of information that makes it difficult to determine its authenticity.

The Ethical and Social Impact of Artificial Intelligence

Latest findings for the use of Knowledge Graph in the field of QA in multiple research directions Author: Xuzeng He (

 ORCID:

0009–0005–7317–7426) Question Answering (QA), the ability to interact with data using natural language questions and obtaining accurate results, has been a long-standing challenge in computer science dating back to the 1960s.

Question Answering enhanced by Knowledge Graph

Unlocking the power of knowledge graphs in research catalogues: A deep dive into OpenAlex


 Author:


 Dhruv Gupta (ORCID:


 0009–0004–7109–5403


 )

Clive Humby, in 2006 rightly said, “Data is the new oil”. With data being present everywhere, it has never been more valuable.

Knowledge Graphs: Deep Dive into OpenAlex

Techniques to integrate Knowledge Graphs into Language Models

 Author

Amanda Kau

 (ORCID:


 0009–0004–4949–9284


 )

Introduction Both knowledge graphs (KGs) and pre-trained language models (PLMs) have gained popularity due to their ability to comprehend world knowledge and their broad applicability.

A Deep Dive Into Knowledge Graph Enhanced Pre-trained Language Models

Automated Knowledge Graph Construction with Large Language Models — Part 2

 Harvesting the Power and Knowledge of Large Language Models

Author Amanda Kau (

 ORCID

:

 0009–0004–4949–9284

) Introduction Knowledge graphs (KGs) are a structured representation of data in a graphical format, in which entities are represented by nodes and are connected by edges representing relationships

Automated Knowledge Graph Construction with Large Language Models — Part 2

An improvement architecture superior to the Transformer, proposed by Meta Author · Qingqin Fang (

 ORCID:

0009–0003–5348–4264) Introduction Recently, researchers from Meta and the University of Southern California have introduced a model called Megalodon. They claim that this model can expand the context window of language models to handle millions of tokens without overwhelming your memory.

The longer the context, the better? Unlimited Context Length in Megalodon

Latest findings in pre-training graphs and using them for link recommendation Author · Xuzeng He (

 ORCID:

0009–0005–7317–7426) Introduction A graph, in short, is a description of items linked by relations, where the items of a graph are called nodes (or vertices) and their relations are called edges (or links). Examples of graphs can include social networks (e.g. Instagram) or knowledge graphs (e.g. Wikipedia). In Instagram

Working with Graphs: Pre-training and Application

Unlocking the Future of AI: The Transformative Journey of Large Language Models Author · Vaibhav Khobragade (

 ORCID:

0009–0009–8807–5982)

 Introduction

Human language development is innate and evolves throughout life. Machines lack this ability to evolve without advanced AI algorithms.

The Journey of Large Language Models: Evolution, Application, and Limitations

Understanding Knowledge Networks From A Graph Perspective


 Author:


 Amanda Kau (ORCID:


 0009–0004–4949–9284


 )

Since 2020, over ten million scholarly articles have been published annually. To put that into perspective, say all ten million articles were released on the first day of the year.

Uncovering The Secrets Behind The Most Influential Scholarly Publications With AceMap

Understanding the Balance between Internal Knowledge and External Sources

Author Qingqin Fang (

 ORCID:

0009–0003–5348–4264) Introduction Previous research often emphasized the limitations of LLM’s information acquisition pathways, focusing on enhancing its capabilities in this regard.

When RAG and LLM Conflict: Who Will AI Listen to?

Solutions to Enhance LLM Performance in Long Contexts Author · Qingqin Fang (

 ORCID:

0009–0003–5348–4264) Introduction In the era of AI breakthroughs, large language models (LLMs) are not just advancements; they are revolutions, transforming how we interact with technology, from casual conversations with chatbots to the intricate mechanisms behind sophisticated data analysis tools.

Navigating the Long Context Conundrum: Challenges in Language Models’ Information Processing

Supervised Fine-tuning, Reinforcement Learning from Human Feedback and the latest SteerLM Author · Xuzeng He (

 ORCID:

0009–0005–7317–7426) Introduction Large Language Models (LLMs), usually trained with extensive text data, can demonstrate remarkable capabilities in handling various tasks with state-of-the-art performance. However, people nowadays typically want something more personalised instead of a general solution.

Fine-tuning Large Language Models: A Brief Introduction

An Overview of Constructing a Knowledge Graph Author · Qingqin Fang (

 ORCID:

0009–0003–5348–4264) 1. Introduction 1.1 What is a Knowledge Graph Knowledge Graphs are structured semantic knowledge bases used to rapidly describe concepts and their relationships in the physical world.

Unlocking Intelligence: The Journey from Data to Knowledge Graph

Author Dhruv Gupta (

 ORCID

: 0009–0004–7109–5403) Introduction Large Language Models (LLMs) have become the new face of Natural language processing (NLP). With their generative power and ability to comprehend human language, the human reliance on these models is increasing every day. However, the LLMs have been known to hallucinate and thus produce wrong outputs.

Prompt engineering: A Way to Smartly Use AI

Latest effort in assessing the security of the code generated by large language models Author · Xuzeng He (

 ORCID:

0009–0005–7317–7426) Introduction With the surge of Large Language Models (LLMs) nowadays, there is a rising trend among developers to use Large Language Models to assist their daily code writing. Famous products include GitHub Copilot or simply ChatGPT.

Large Language Models for Code Writing: Security Assessment

Research Graph

Google’s Groundbreaking AI Model Explained
 


 Introduction

In the rapidly evolving landscape of artificial intelligence, Google continues to stand at the forefront, consistently pushing the boundaries of what these technologies can achieve. One of their latest advancements, GEMMA2, represents a significant leap in AI capabilities.

What is Gemma2?

Stories by Research Graph on Medium

**Understanding Knowledge Networks From A Graph Perspective**

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*EfInqfXKiK2qI4IU" />
<figcaption>Source: <a
href="https://unsplash.com/photos/open-book-lot-Oaqk7qqNh_c">https://unsplash.com/photos/open-book-lot-Oaqk7qqNh_c</a></figcaption>
</figure>

#### **Author:**

- **Amanda Kau (ORCID:**
 [**0009--0004--4949--9284**](https://orcid.org/0009-0004-4949-9284)**)**

Since 2020, over ten million scholarly articles have been published
annually. To put that into perspective, say all ten million articles
were released on the first day of the year. To get through them all, you
would have to read about 27,397 articles every single day. Even if you
were only interested in a specific field like artificial intelligence
(AI), with 242,375 articles about AI in AceMap's database in 2020 alone,
that is still 664 articles daily.

We all agree that this is a staggering volume of articles that poses
significant issues. For instance, governments struggle to choose which
endeavours to allocate research funding to. Organisations face
difficulties in recognising influential works deserving of awards like
Turing Awards or Nobel Prizes. Researchers grapple with identifying
research trends to do further exploration. Several factors make this
more challenging:

- The structure of platforms that researchers commonly turn to, such as
 academic search engines like Google Scholar or pre-print platforms
 like arXiv, lack the structure to easily analyse interactions between
 publications and academic entities. Imagine you were given a long list
 of PDF documents, it would be hard to connect them all to spot trends
 or to compare them.
- Current metrics like citation counts only partially capture a
 paper's impact.
- Tools for citation analysis, such as CiteSpace and CitNetExplorer, do
 not specifically identify or quantify the influence of publications.

This article will review the [**AceMap**](https://www.acemap.info/)
system and introduce several features of the AceMap interface. Then, the
**Scientific X-ray** framework, designed to quantify the influence of
publications using AceMap data, will be introduced with some interesting
findings.

### What Is AceMap?

[AceMap](https://www.acemap.info/) is a database system that connects
academic entities in a knowledge graph called **AceKG** (AceMap
Knowledge Graph). Containing more than 221 million papers from 1800 to
2021, by more than 103 million authors across 767 thousand different
research fields, AceMap was designed to address four fundamental
questions:

1. How do we effectively represent complex interactions between
 entities?
2. What is an intuitive method to represent the structure of the
 scholarly network?
3. How can we measure the knowledge possessed by entities for
 comparison?
4. How can we analyse these networks and present the findings in a
 digestible way?

We will briefly discuss each of these aspects in relation to AceMap's
features.

#### 1. How do we effectively represent complex interactions between entities? {#how-do-we-effectively-represent-complex-interactions-between-entities}

AceMap is built on AceKG, and a diagram of its main components is shown
in the image below. The graph comprises five classes of entities
represented by icons --- papers, authors, venues, fields of study and
institutes --- totalling over 114 million entities. Each entity has
several properties such as name or publish date, represented by hollow
circles, while the relationships between entities are represented by
black arrows.

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*9OIP3g3tSUvJwqQ8" />
<figcaption>The AceKG Ontology. Source: Wang et al., 2024 <a
href="https://doi.org/10.48550/arXiv.2403.02576">https://doi.org/10.48550/arXiv.2403.02576</a></figcaption>
</figure>

This graphical representation allows further connections to be made:

- **Topic Tree:** Hierarchical relationships can be formed by studying
 co-occurrence of concepts. For instance, the field of model-based
 reasoning, which is an inference method for artificial intelligence
 systems to model the real world, has the following parent and
 children topics.

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*Rvvq-1yAr3B0MYbW" />
<figcaption>Example of parent and children topics for topic “Model-based
reasoning”. Obtained on 14 March 2024 from AceMap, <a
href="https://www.acemap.info/field/2044117001">https://www.acemap.info/field/2044117001</a></figcaption>
</figure>

- **Tracing and Evolution Tree:** Accessible from the IdeaReader section
 of each publication's webpage, the tracing tree details past papers
 that motivated the current paper, while the evolution tree maps out
 the current paper's influence on subsequent works.
- **Paper Map of Field:** Papers that define every field, like
 "Model-based reasoning" in the example here, are listed out based on
 first authors. The links between these papers are represented as well.

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*gNqHzW9Je24S2CPr" />
<figcaption>Paper map of field for the field “Model-based reasoning”.
Obtained on 14 March 2024 from AceMap, <a
href="https://www.acemap.info/map/paperMap/2044117001?type=papermap_4">https://www.acemap.info/map/paperMap/2044117001?type=papermap_4</a></figcaption>
</figure>

- **DeepReport:** This novel research assistant system analyses
 co-occurrence and convergence of concepts to identify new ideas by
 combining current ones.

The details of the many natural language processing, data extraction,
and other machine learning techniques that were employed to construct
AceKG can be found in the AceMap paper itself (see the references in the
last section of this post).

#### 2. What is an intuitive method to represent the structure of the scholarly network? {#what-is-an-intuitive-method-to-represent-the-structure-of-the-scholarly-network}

Existing visualisation methods were inadequate to display the vastness
of AceKG, as they handle only up to hundreds of thousands of nodes, far
from AceKG's millions. Instead, a new method called **VSAN**
(Visualising Super-Large Academic Networks) was proposed. Essentially,
the graph was divided into smaller segments which were displayed
separately and stitched together.

Four million nodes and 36 million edges from the DBLP computer science
bibliography were mapped onto a galaxy-like graph. In the image below,
in panel (c), computer vision conferences like CVPR and ICCV were
clearly clustered. Panels (d) and (e) show topic clusters in the
computer networks field and in an information theory journal.

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*MgbUg4qYyAQu006g" />
<figcaption>Galaxy-like structures could be mapped out using VSAN.
Source: Wang et al., 2024 <a
href="https://doi.org/10.48550/arXiv.2403.02576">https://doi.org/10.48550/arXiv.2403.02576</a></figcaption>
</figure>

#### 3. How can we measure the knowledge possessed by entities for comparison? {#how-can-we-measure-the-knowledge-possessed-by-entities-for-comparison}

Instead of using citation-based metrics to measure knowledge, the
**Knowledge Quantification Index** (KQI) based on entropy was proposed.
A higher KQI is assigned to publications with better acceptability and
dependability, meaning the paper was derived from reliable parent
knowledge and inspires numerous subsequent works. KQI offers several
advantages over other metrics:

- It considers the flow of ideas from paper to paper.
- It cannot be manipulated by self-citation or citation stacking,
 wherein authors repeatedly cite their own works to inflate
 citation counts.
- It can pinpoint valuable knowledge.

In fact, when ordering the top 10,000 authors by KQI from their computer
science dataset, the creators of AceMap identified 71 Turing Award
winners, amounting to 96% of all winners up to 2020.

#### 4. How can we analyse these networks and present the findings in a digestible way? {#how-can-we-analyse-these-networks-and-present-the-findings-in-a-digestible-way}

Besides the numerous graphs and charts presented on the AceMap website,
there is an additional feature called **IdeaReader**. In a snapshot of
IdeaReader's interface below, information regarding the target paper is
provided to the user in panel (1), including the list of authors,
abstract and several metrics. IdeaReader identifies papers most likely
to inspire or be influenced by the target publication. Automatically
generated summaries of the top five papers in these two groups are
provided in panels (2) and (3). The flow of ideas from papers before and
after the target paper are also given in panel (4).

<figure>
<img
src="https://cdn-images-1.medium.com/max/1024/1*lGO4jmCv1jxCV18uab1BFw.png" />
<figcaption>Information provided by IdeaReader for the paper “Attention
Is All You Need”. Source: Wang et al., 2024 <a
href="https://doi.org/10.48550/arXiv.2403.02576">https://doi.org/10.48550/arXiv.2403.02576</a></figcaption>
</figure>

### Scientific X-ray: A Framework Built on AceMap's Database

In 2022, the **Scientific X-ray** framework was proposed by Li and
colleagues to help evaluate the development and potential of ideas, to
identify them amidst the vast array of publications. Citation networks
(depicted as tree structures in the image) were constructed for each
target publication (depicted as pink circles). Distinct network
structures were observed for different publications, like the top
structure in panel (b) in the image below representing summative work
like textbooks, and the bottom structure showing innovative research.
The 'idea' tree in panel (c) was formed to represent the flow of ideas
to subsequent papers. Based on these trees, three metrics were
introduced:

1. **Knowledge Entropy** (KE): Quantifies knowledge within a paper
 based on its tree's structure.
2. **Valid Depth** (VD): Measures the degree of development of the
 target publication's idea.
3. **Development Potential Index** (DPI): Assesses future potential of
 the target publication's idea.

<figure>
<img
src="https://cdn-images-1.medium.com/max/1024/1*i6NYZuHnMSk-kRsClCP3JA.png" />
<figcaption>The framework of Scientific X-ray. Source: Li et al., 2022
<a
href="https://doi.org/10.1371/journal.pone.0275192">https://doi.org/10.1371/journal.pone.0275192</a></figcaption>
</figure>

Noteworthy findings were discovered using these metrics. Firstly, a
significant proportion (31.11%) of publications had a VD of zero,
showing challenges in new knowledge being adopted. Secondly, although
citation counts could increase indefinitely, 99% of publications could
not exceed the upper bound of influence at a VD of six. Furthermore, the
evolution of ideas across disciplines followed six distinct patterns
automatically derived from idea trees:

1. Summative work, like textbooks, lacked the ability to inspire future
 works or foster new ideas.
2. Continued development of a target article's idea needed subsequent
 works which were also influential.
3. A relay of influential subsequent works was necessary for the
 continued development of the target publication's idea.
4. Subsequent work that overshadowed the target publication caused the
 original idea to lose relevance and attention.
5. If two branches of thought followed from the target publication, the
 dominance of one branch impeded development in the second branch.
6. Publications approaching the upper limit of development required
 many influential subsequent works to sustain progress.

Meanwhile, by assessing DPI, Scientific X-ray accurately identified 40
out of 49 Nobel Prize topics in Physics, Chemistry, and Physiology or
Medicine from 1900 to 2016, demonstrating the effectiveness of DPI in
predicting the influence of scientific ideas.

### Conclusion

We have introduced the **AceMap** system, which relies on the knowledge
graph **AceKG**, showcasing various features including the tracing and
evolution trees, IdeaReader, and DeepReport. A new visualisation
technique for massive graphs, **Visualising Super-Large Academic
Networks** (VSAN), was presented. We also discussed the **Scientific
X-ray** framework based on AceMap data and presented six interesting
patterns regarding idea development in scientific research. Furthermore,
we explored four novel metrics --- the **Knowledge Quantification
Index** (KQI), **Knowledge Entropy** (KE), **Valid Depth** (VD), and
**Development Potential Index** (DPI) --- as means to measure the
knowledge, development, and potential of publications.

#### **References**

Wang, X., Fu, L., Gan, X., Wen, Y., Zheng, G., Ding, J., Xiang, L., Ye,
N., Jin, M., Liang, S., Lu, B., Wang, H., Xu, Y., Deng, C., Zhang, S.,
Kang, H., Wang, X., Li, Q., Guo, Z., ... Zhou, C. (2024). AceMap:
Knowledge Discovery through Academic Graph (Version 1). arXiv.
<https://doi.org/10.48550/ARXIV.2403.02576>

Li, Q., Wang, X., Fu, L., Wang, J., Yao, L., Gan, X., & Zhou, C. (2022).
Scientific X-ray: Scanning and quantifying the idea evolution of
scientific publications. In E. Caroselli (Ed.), PLOS ONE (Vol. 17, Issue
9, p. e0275192). Public Library of Science (PLoS).
<https://doi.org/10.1371/journal.pone.0275192>

![](https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=1a6f5ee7921b){width="1"
height="1"}

**Unlocking the power of knowledge graphs in research catalogues: A deep
dive into OpenAlex**

<figure>
<img
src="https://cdn-images-1.medium.com/max/1000/0*vz8OrFW6N2e-vdwz" />
<figcaption>Image from Unsplash.</figcaption>
</figure>

### **Author:**

- **Dhruv Gupta (ORCID:**
 [**0009--0004--7109--5403**](https://orcid.org/0009-0004-7109-5403)**)**

Clive Humby, in 2006 rightly said, "Data is the new oil". With data
being present everywhere, it has never been more valuable. With
companies using data to make smarter decisions its storage is slowly
becoming an issue. This is where Knowledge Graphs come into the
equation. In this article, we will talk about what knowledge graphs are
followed by a deep dive into Open Alex.

### **What Are Knowledge Graphs?**

The term knowledge graph was first used by Google in 2012 to refer to
its knowledge base. These graphs help organise data from different
sources, capture information about stakeholders and try to build
connections among them. With applications ranging from search engines,
chatbots, and recommendation systems knowledge graphs are everywhere.
Knowledge graphs are being widely used in the field of machine learning
as well. They complement machine learning tasks by:

- Reducing the need for large labelled datasets
- Allow transfer learning
- Allows cross-domain learning by building connections

<figure>
<img src="https://cdn-images-1.medium.com/max/589/0*GuNQ6pxjNRAwLIQX" />
<figcaption>An example of a Knowledge Graph. Source: Research Graph
Foundation <a
href="https://researchgraph.org/">https://researc​​hgraph.org/</a>.</figcaption>
</figure>

The use of knowledge graphs has seen an increase in text-related tasks.
Big graphs can provide background knowledge, human-like awareness and
concepts.

In addition to this knowledge-graphs are being used a lot for research
purposes as well. A lot of research databases such as OpenAlex,
Dimensions, and the Lens are being utilised to help researchers. These
tools help the researchers by giving them appropriate metadata such as
bibliographical knowledge, publications, and citations which can be
utilised to further enhance their research.

### **Open Alex**

Microsoft Academic Graph (MAG) was first launched in 2015. Since its
first public appearance, MAG has served as a promising new data source
for researchers, due to its rich bibliographic analysis and large
coverage and availability of metadata. However, in 2021 via its blog,
MAG announced that it would retire on 31st December. Soon after that
OurResearch announced that they would incorporate the last full MAG
corpus excluding the patent data to create a new graph called OpenAlex.
OpenAlex which was first launched in January 2022 also incorporated data
from CrossRef, another source of large data. OpenAlex was launched with
open API access to both their services and any form of data dumps.
OpenAlex dataset is a heterogeneous directed graph composed of five
types of scholarly entities and connections. The data in these entities
is represented by a unique ID called CEID (Canonical External ID).

<figure>
<img src="https://cdn-images-1.medium.com/max/548/0*QbBh0Z2tf30Zu6lD" />
<figcaption>Basic Knowledge Graph showing different entities in
OpenAlex.</figcaption>
</figure>

The different entities serve purposes as listed below:

- **Works**: contains scholarly documents such as journal articles,
 books, databases, and theses. The CEID for works is DOI.
- **Authors**: contains people who create works. There are approximately
 213M authors in OpenAlex. The CEID for authors is ORCID. They are
 connected to works via authorship.
- **Venues**: defined as places that host works. There are roughly
 124000 venues in OpenAlex. The CEID for venues is ISSN-L.
- **Institutions**: are organisations to which authors claim
 affiliations. There are roughly 109000 institutions in OpenAlex. The
 CEID for institutions is ROR-ID.
- **Concepts**: These are the abstract ideas works are about. There are
 approximately 65000 concepts in OpenAlex. The CEID for concepts is
 Wikidata ID.

OpenAlex contains approximately 240M works with 50000 being added daily
onto the graph. These works include scholarly articles which are further
divided into 26 document types which further inherit its definitions
from CrossRef.

#### **Open access**

There are three ways to obtain data from OpenAlex:

- A full data dump is updated every fortnight
- REST API calls are updated daily
- Web-based GUI

All of these methods are free and require no registration or permission.
The code behind OpenAlex is fully open source and is available on the
OurResearch Github account as well.

#### **OpenAlex vs MAG**

Even though OpenAlex is still quite young it has practically transferred
all works from MAG preserving almost all the metadata that is useful.
More than 90% of the MAG documents have an equivalent document type in
OpenAlex. In addition to this, the reclassification of documents done by
OpenAlex has proven to be valid which has improved the quality of
research. Moreover, the papers in OpenAlex have better Field of Study
(FoS) assignments. As we go deeper into the graph the FoS difference
is drastic.

### **Limitations and Future Work**

OpenAlex as a knowledge graph is still very young and there are areas
for improvement. It needs to make sure that there are no disambiguates
among the entities, especially authors and institutions. The dataset
also needs to add certain metadata values such as funding sources, as
well as data about corresponding authors. However, this being said the
researchers have done a great job in building a dataset which shows
great promise as an alternative for MAG.

#### Sources

- Priem, J., Piwowar, H., & Orr, R. (2022). OpenAlex: A fully-open index
 of scholarly works, authors, venues, institutions, and concepts
 (Version 2). arXiv. DOI: 10.48550/ARXIV.2205.01833
- Jiao, C., Li, K., & Fang, Z. (2023). How are exclusively data journals
 indexed in major scholarly databases? An examination of the Web of
 Science, Scopus, Dimensions, and OpenAlex (Version 1). arXiv. DOI:
 10.48550/ARXIV.2307.09704
- Scheidsteger, T., & Haunschild, R. (2023). Which of the metadata with
 relevance for bibliometrics are the same and which are different when
 switching from Microsoft Academic Graph to OpenAlex? In El Profesional
 de la información. Ediciones Profesionales de la Informacion SL.
 DOI:10.3145/epi.2023.mar.09
- Ontotext. What is a Knowledge Graph?
 <https://www.ontotext.com/knowledgehub/fundamentals/what-is-a-knowledge-graph/>

![](https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=024941f2cfb2){width="1"
height="1"}