Exploring and Verbalizing Academic Ideas by Concept Co-occurrence
Xu, Yi, Sheng, Shuqian, Xue, Bo, Fu, Luoyi, Wang, Xinbing, Zhou, Chenghu
–arXiv.org Artificial Intelligence
Researchers usually come up with new ideas only after thoroughly comprehending vast quantities of literature. The difficulty of this procedure is exacerbated by the fact that the number of academic publications is growing exponentially. In this study, we devise a framework based on concept co-occurrence for academic idea inspiration, which has been integrated into a research assistant system. From our perspective, the fusion of two concepts that co-occur in an academic paper can be regarded as an important way of the emergence of a new idea. We construct evolving concept graphs according to the co-occurrence relationship of concepts from 20 disciplines or topics. Then we design a temporal link prediction method based on masked language model to explore potential connections between different concepts. To verbalize the newly discovered connections, we also utilize the pretrained language model to generate a description of an idea based on a new data structure called co-occurrence citation quintuple. We evaluate our proposed system using both automatic metrics and human assessment. The results demonstrate that our system has broad prospects and can assist researchers in expediting the process of discovering new ideas.
arXiv.org Artificial Intelligence
Jun-4-2023
- Country:
- Asia > China (0.46)
- Europe > United Kingdom (0.14)
- Africa (0.14)
- North America > United States
- Texas (0.14)
- Genre:
- Research Report > New Finding (1.00)
- Industry:
- Banking & Finance > Economy (1.00)
- Education (1.00)
- Law > Civil Rights & Constitutional Law (1.00)
- Government > Regional Government (0.93)
- Information Technology > Security & Privacy (0.93)
- Media > Music (0.92)
- Leisure & Entertainment (0.92)
- Energy
- Oil & Gas > Upstream (1.00)
- Renewable > Geothermal (0.93)
- Health & Medicine
- Pharmaceuticals & Biotechnology (1.00)
- Epidemiology (0.94)
- Therapeutic Area
- Pulmonary/Respiratory Diseases (1.00)
- Oncology (1.00)
- Neurology (1.00)
- Infections and Infectious Diseases (1.00)
- Immunology (1.00)
- Psychiatry/Psychology > Mental Health (0.46)
- Materials
- Chemicals (1.00)
- Metals & Mining (0.92)
- Technology:
- Information Technology
- Security & Privacy (1.00)
- Information Management (1.00)
- Human Computer Interaction (1.00)
- Data Science > Data Mining (1.00)
- Communications (1.00)
- Artificial Intelligence
- Cognitive Science (1.00)
- Representation & Reasoning > Agents (0.93)
- Natural Language > Large Language Model (0.68)
- Machine Learning
- Evolutionary Systems (0.67)
- Statistical Learning (0.67)
- Neural Networks > Deep Learning (0.46)
- Information Technology