Question-focused Summarization by Decomposing Articles into Facts and Opinions and Retrieving Entities

TL;DR

This paper presents a method for question-focused summarization of news articles by decomposing them into facts and opinions, then retrieving relevant entities to generate concise summaries for financial analysis.

Contribution

It introduces a novel approach combining fact-opinion decomposition and entity retrieval to improve targeted summarization in financial news analysis.

Findings

Effective identification of salient facts and entities from articles.

Enhanced summaries that capture key market-changing information.

Potential for early detection of market trends using the proposed method.

Abstract

This research focuses on utilizing natural language processing techniques to predict stock price fluctuations, with a specific interest in early detection of economic, political, social, and technological changes that can be leveraged for capturing market opportunities. The proposed approach includes the identification of salient facts and events from news articles, then use these facts to form tuples with entities which can be used to get summaries of market changes for particular entity and then finally combining all the summaries to form a final abstract summary of the whole article. The research aims to establish relationships between companies and entities through the analysis of Wikipedia data and articles from the Economist. Large Language Model GPT 3.5 is used for getting the summaries and also forming the final summary. The ultimate goal of this research is to develop a comprehensive system that can provide financial analysts and investors with more informed decision-making tools by enabling early detection of market trends and events.