Automatic Numerical Question Answering on Table using BERT-GNN

Bagwe, Ruchi; George, Kiran

doi:10.1109/uemcon51285.2020.9298028

2020 11th IEEE Annual Ubiquitous Computing, Electronics &Amp; Mobile Communication Conference (UEMCON) 2020

DOI: 10.1109/uemcon51285.2020.9298028

|View full text |Cite

Automatic Numerical Question Answering on Table using BERT-GNN

Ruchi Bagwe

Kiran George

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2022

2023

Publication Types

Select...

Article2

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

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

Suissa

Zhitomirsky‐Geffet

Elmalech

2023

J. Comput. Cult. Herit.

View full text Add to dashboard Cite

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.

show abstract

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

Suissa

Zhitomirsky‐Geffet

Elmalech

2023

J. Comput. Cult. Herit.

View full text Add to dashboard Cite

show abstract

Chatbot basado en una versión ligera del modelo BERT para resolver inquietudes relacionadas con matrículas y homologaciones en la Universidad Nacional de Loja

Paredes

Figueroa-Diaz

2022

CEDAMAZ

View full text Add to dashboard Cite

En este artículo se presenta el desarrollo de un chatbot utilizando como red neuronal una versión ligera del modelo BERT denominado DistilBERT, que ayude a estudiantes o profesionales a solventar inquietudes con respecto a matrículas y homologaciones para los estudios de cuarto nivel o posgrados en la Universidad Nacional de Loja (UNL). En este contexto, el proyecto se dividió en dos etapas: en la primera, se hizo una búsqueda bibliográfica en artículos científicos sobre las tecnologías y herramientas compatibles para realizar el ajuste del modelo BERT mediante un entrenamiento en la tarea de preguntas y respuestas; en la segunda etapa, se llevó a cabo el desarrollo del chatbot siguiendo la metodología de Programación Extrema (XP) dividida en cuatro fases: planeación, diseño, codificación y pruebas. En la fase de planeación, se llevó a cabo el entrenamiento del modelo, requisito necesario para la implementación del chatbot. En esta fase se especificaron los parámetros para el entrenamiento modelo y la descripción de forma general del funcionamiento del agente conversacional mediante historias de usuario. En la segunda fase se diseñó la arquitectura, en la que se muestran todos los elementos que formaron parte del chatbot. En la tercera fase se llevó a cabo la programación utilizando los lenguajes de programación Python, JavaScript, Css, Html y el microframework Flask. Finalmente, en la última fase se ejecutaron pruebas de rendimiento, carga y estrés para ver el comportamiento del chatbot al ser sometido a una carga considerable de peticiones.

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Automatic Numerical Question Answering on Table using BERT-GNN

Cited by 2 publications

References 17 publications

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

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

Chatbot basado en una versión ligera del modelo BERT para resolver inquietudes relacionadas con matrículas y homologaciones en la Universidad Nacional de Loja

Contact Info

Product

Resources

About