Efficient Answer Retrieval System (EARS): Combining Local DB Search and Web Search for Generative QA
Nikita Krayko, Ivan Sidorov, Fedor Laputin, Daria Galimzianova, Vasily Konovalov
Abstract
In this work, we propose an efficient answer retrieval system **EARS**: a production-ready, factual question answering (QA) system that combines local knowledge base search with generative, context-based QA. To assess the quality of the generated content, we devise comprehensive metrics for both manual and automatic evaluation of the answers to questions. A distinctive feature of our system is the Ranker component, which ranks answer candidates based on their relevance. This feature enhances the effectiveness of local knowledge base retrieval by 23%. Another crucial aspect of our system is the LLM, which utilizes contextual information from a web search API to generate responses. This results in substantial 92.8% boost in the usefulness of voice-based responses. **EARS** is language-agnostic and can be applied to any data domain.
BibTeX
@inproceedings{krayko-etal-2024-efficient,
title = "Efficient Answer Retrieval System ({EARS}): Combining Local {DB} Search and Web Search for Generative {QA}",
author = "Krayko, Nikita and
Sidorov, Ivan and
Laputin, Fedor and
Galimzianova, Daria and
Konovalov, Vasily",
editor = "Dernoncourt, Franck and
Preo{\c{t}}iuc-Pietro, Daniel and
Shimorina, Anastasia",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2024",
address = "Miami, Florida, US",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-industry.116/",
doi = "10.18653/v1/2024.emnlp-industry.116",
pages = "1584--1594"
}