Around the GLOBE: Numerical Aggregation Question-answering on Heterogeneous Genealogical Knowledge Graphs with Deep Neural Networks

Abstract

One of the key AI tools for textual corpora exploration is natural language question-answering (QA). Unlike keyword-based search engines, QA algorithms receive and process natural language questions and produce precise answers to these questions, rather than long lists of documents that need to be manually scanned by the users. State-of-the-art QA algorithms based on DNNs were successfully employed in various domains. However, QA in the genealogical domain is still underexplored, while researchers in this field (and other fields in humanities and social sciences) can highly benefit from the ability to ask questions in natural language, receive concrete answers and gain insights hidden within large corpora. While some research has been recently conducted for factual QA in the genealogical domain, to the best of our knowledge, there is no previous research on the more challenging task of numerical aggregation QA (i.e., answering questions combining aggregation functions, e.g., count, average, max). Numerical aggregation QA is critical for distant reading and analysis for researchers (and the general public) interested in investigating cultural heritage domains. Therefore, in this study, we present a new end-to-end methodology for numerical aggregation QA for genealogical trees that includes: 1) an automatic method for training dataset generation; 2) a transformer-based table selection method, and 3) an optimized transformer-based numerical aggregation QA model. The findings indicate that the proposed architecture, GLOBE, outperforms the state-of-the-art models and pipelines by achieving 87% accuracy for this task compared to only 21% by current state-of-the-art models. This study may have practical implications for genealogical information centers and museums, making genealogical data research easy and scalable for experts as well as the general public.

AI‐Based Research Tool for Large Genealogical Corpora: The Case of Jewish Communities Worldwide

“…data was much higher than that of the original state-of-the-art single-table TaPas model (87% vs. 21%). A detailed description of the model and experiments is presented in Suissa et al, (2023).…”

“…the erformed above ). Technical details of the model implementation are described in Suissa et al(2023).…”

“…This was performed by “breaking” the question into two questions and calculating the “main” question's answer divided by the question's population (e.g., for the question above ” the model will calculate ). Technical details of the model implementation are described in Suissa et al(2023).…”

Word Vectors for Criticism of a Korean Film - 'Decision to Leave' by Chanwook Park

“…Language models can assist in this by highlighting words that frequently appear in a specific context or have a strong association with a particular topic. These keywords can be used for indexing, search engine optimization, or summarization [7][8][9]. Document Classification: Through sentiment analysis, topic extraction, and keyword selection, documents can be classified based on specific criteria.…”

“…(1) Mountain/Sea : murder/suicide, doubt/love, investigation/compassion, man/woman, detective/suspect (2) Pusan/Leepoh: mountain/sea, incident/safety, city/rural (3) Green/Blue: mountain/sea (4) Jellyfish/Turtle: sleeping/unsleeping (5) Fog: dual image of safe and dangerous (6) Negative images: maggots, ice cream, nuclear power plant, mountain, turtle (7) Positive images: fried rice, sea, jellyfish (8) Dramatic images: collapse, unresolved case, abandonment in the depths of the sea Although we can summarize various images and symbols in the movie like this, it is uncertain whether the devices, places, and characters expressed in the movie actually have such features. Therefore, it is necessary to determine the authenticity by analyzing the nature of the words indicated by each place/device/person using word vectors that can be obtained using a recurrent neural network, a type of deep learning technique.…”