Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userThe Emerging Scholarly Brain
205
0
0.0
(
0
)
Authors
Michael J. Kurtz
Ask ChatGPT about the research
No Arabic abstract
It is now a commonplace observation that human society is becoming a coherent super-organism, and that the information infrastructure forms its emerging brain. Perhaps, as the underlying technologies are likely to become billions of times more powerful than those we have today, we could say that we are now building the lizard brain for the future organism.
rate research
Read More
Citation measures, and newer altmetric measures such as downloads are now commonly used to inform personnel decisions. How well do or can these measures measure or predict the past, current of future scholarly performance of an individual? Using data from the Smithsonian/NASA Astrophysics Data System we analyze the publication, citation, download, and distinction histories of a cohort of 922 individuals who received a U.S. PhD in astronomy in the period 1972-1976. By examining the same and different measures at the same and different times for the same individuals we are able to show the capabilities and limitations of each measure. Because the distributions are lognormal measurement uncertainties are multiplicative; we show that in order to state with 95% confidence that one persons citations and/or downloads are significantly higher than another persons, the log difference in the ratio of counts must be at least 0.3 dex, which corresponds to a multiplicative factor of two.
Bibliometric indicators, citation counts and/or download counts are increasingly being used to inform personnel decisions such as hiring or promotions. These statistics are very often misused. Here we provide a guide to the factors which should be considered when using these so-called quantitative measures to evaluate people. Rules of thumb are given for when begin to use bibliometric measures when comparing otherwise similar candidates.
Answering questions on scholarly knowledge comprising text and other artifacts is a vital part of any research life cycle. Querying scholarly knowledge and retrieving suitable answers is currently hardly possible due to the following primary reason: machine inactionable, ambiguous and unstructured content in publications. We present JarvisQA, a BERT based system to answer questions on tabular views of scholarly knowledge graphs. Such tables can be found in a variety of shapes in the scholarly literature (e.g., surveys, comparisons or results). Our system can retrieve direct answers to a variety of different questions asked on tabular data in articles. Furthermore, we present a preliminary dataset of related tables and a corresponding set of natural language questions. This dataset is used as a benchmark for our system and can be reused by others. Additionally, JarvisQA is evaluated on two datasets against other baselines and shows an improvement of two to three folds in performance compared to related methods.
In previous studies, much attention from multidisciplinary fields has been devoted to understand the mechanism of underlying scholarly networks including bibliographic networks, citation networks and co-citation networks. Particularly focusing on networks constructed by means of either authors affinities or the mutual content. Missing a valuable dimension of network, which is an audience scholarly paper. We aim at this paper to assess the impact that social networks and media can have on scholarly papers. We also examine the process of information flow in such networks. We also mention some observa- tions of attractive incidents that our proposed network model revealed.
The incompleteness of Knowledge Graphs (KGs) is a crucial issue affecting the quality of AI-based services. In the scholarly domain, KGs describing research publications typically lack important information, hindering our ability to analyse and predict research dynamics. In recent years, link prediction approaches based on Knowledge Graph Embedding models became the first aid for this issue. In this work, we present Trans4E, a novel embedding model that is particularly fit for KGs which include N to M relations with N$gg$M. This is typical for KGs that categorize a large number of entities (e.g., research articles, patents, persons) according to a relatively small set of categories. Trans4E was applied on two large-scale knowledge graphs, the Academia/Industry DynAmics (AIDA) and Microsoft Academic Graph (MAG), for completing the information about Fields of Study (e.g., neural networks, machine learning, artificial intelligence), and affiliation types (e.g., education, company, government), improving the scope and accuracy of the resulting data. We evaluated our approach against alternative solutions on AIDA, MAG, and four other benchmarks (FB15k, FB15k-237, WN18, and WN18RR). Trans4E outperforms the other models when using low embedding dimensions and obtains competitive results in high dimensions.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
