What question did this study set out to answer?

This research aims to analyze various methods for automating question answering from Portuguese FAQs.

January 1, 2022Open Access

Analysing Off-The-Shelf Options for Question Answering with Portuguese FAQs

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial compares different technologies for answering Portuguese FAQs, suggesting optimal approaches for accuracy and efficiency.

This research aims to analyze various methods for automating question answering from Portuguese FAQs.
Evaluated multiple technologies for question answering including traditional information retrieval and deep neural networks.
Measured configuration effort, answer accuracy, and response time across different methods.
Utilized a dataset of Portuguese telecommunications FAQs for experimental analysis.
Traditional information retrieval shows effectiveness for smaller FAQ lists but has limitations with larger sets.
Deep neural networks for sentence encoding provide reliable answers regardless of FAQ complexity.
Findings indicate deep learning methods require less dependency on the quantity and intricacy of FAQs.

Zhang et al. (2022) studied this question.

View Full Paper

Ask AI

Bookmark

Randomized trial compares different technologies for answering Portuguese FAQs, suggesting optimal approaches for accuracy and efficiency.