NSTM: Real-Time Query-Driven News Overview Composition at Bloomberg

TL;DR

NSTM is a real-time, query-driven news summarization system at Bloomberg that filters, clusters, and summarizes large volumes of news to provide concise, relevant updates with sub-second latency.

Contribution

The paper introduces NSTM, a novel system combining semantic clustering and summarization to efficiently generate personalized news digests at scale.

Findings

Operates with sub-second latency for thousands of requests daily.

Effectively filters noise and duplicates to identify key news.

Provides comprehensive, concise summaries tailored to user queries.

Abstract

Millions of news articles from hundreds of thousands of sources around the globe appear in news aggregators every day. Consuming such a volume of news presents an almost insurmountable challenge. For example, a reader searching on Bloomberg's system for news about the U.K. would find 10,000 articles on a typical day. Apple Inc., the world's most journalistically covered company, garners around 1,800 news articles a day. We realized that a new kind of summarization engine was needed, one that would condense large volumes of news into short, easy to absorb points. The system would filter out noise and duplicates to identify and summarize key news about companies, countries or markets. When given a user query, Bloomberg's solution, Key News Themes (or NSTM), leverages state-of-the-art semantic clustering techniques and novel summarization methods to produce comprehensive, yet concise, digests to dramatically simplify the news consumption process. NSTM is available to hundreds of thousands of readers around the world and serves thousands of requests daily with sub-second latency. At ACL 2020, we will present a demo of NSTM.