RA-MTR: A Retrieval Augmented Multi-Task Reader based Approach for Inspirational Quote Extraction from Long Documents

TL;DR

This paper introduces RA-MTR, a retrieval-augmented multi-task framework for extracting the most relevant inspirational quotes from long texts, significantly improving accuracy over previous methods.

Contribution

It presents a novel multi-task approach combined with retrieval techniques for quote extraction, along with curated datasets and state-of-the-art performance improvements.

Findings

Achieved up to 5.08% improvement in BoW F1-score

Developed three new quote extraction datasets

Demonstrated effectiveness of retrieval-augmented multi-task framework

Abstract

Inspirational quotes from famous individuals are often used to convey thoughts in news articles, essays, and everyday conversations. In this paper, we propose a novel context-based quote extraction system that aims to extract the most relevant quote from a long text. We formulate this quote extraction as an open domain question answering problem first by employing a vector-store based retriever and then applying a multi-task reader. We curate three context-based quote extraction datasets and introduce a novel multi-task framework RA-MTR that improves the state-of-the-art performance, achieving a maximum improvement of 5.08% in BoW F1-score.