@inproceedings{bambrick-etal-2020-nstm,
title = "{NSTM}: Real-Time Query-Driven News Overview Composition at {B}loomberg",
author = "Bambrick, Joshua and
Xu, Minjie and
Almonte, Andy and
Malioutov, Igor and
Perarnau, Guim and
Selo, Vittorio and
Chan, Iat Chong",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-demos.40",
doi = "10.18653/v1/2020.acl-demos.40",
pages = "350--361",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bambrick-etal-2020-nstm">
<titleInfo>
<title>NSTM: Real-Time Query-Driven News Overview Composition at Bloomberg</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Bambrick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjie</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andy</namePart>
<namePart type="family">Almonte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Igor</namePart>
<namePart type="family">Malioutov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guim</namePart>
<namePart type="family">Perarnau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vittorio</namePart>
<namePart type="family">Selo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iat</namePart>
<namePart type="given">Chong</namePart>
<namePart type="family">Chan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-jul</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">bambrick-etal-2020-nstm</identifier>
<identifier type="doi">10.18653/v1/2020.acl-demos.40</identifier>
<location>
<url>https://aclanthology.org/2020.acl-demos.40</url>
</location>
<part>
<date>2020-jul</date>
<extent unit="page">
<start>350</start>
<end>361</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NSTM: Real-Time Query-Driven News Overview Composition at Bloomberg
%A Bambrick, Joshua
%A Xu, Minjie
%A Almonte, Andy
%A Malioutov, Igor
%A Perarnau, Guim
%A Selo, Vittorio
%A Chan, Iat Chong
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
%D 2020
%8 jul
%I Association for Computational Linguistics
%C Online
%F bambrick-etal-2020-nstm
%X 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.
%R 10.18653/v1/2020.acl-demos.40
%U https://aclanthology.org/2020.acl-demos.40
%U https://doi.org/10.18653/v1/2020.acl-demos.40
%P 350-361
Markdown (Informal)
[NSTM: Real-Time Query-Driven News Overview Composition at Bloomberg](https://aclanthology.org/2020.acl-demos.40) (Bambrick et al., ACL 2020)
ACL
- Joshua Bambrick, Minjie Xu, Andy Almonte, Igor Malioutov, Guim Perarnau, Vittorio Selo, and Iat Chong Chan. 2020. NSTM: Real-Time Query-Driven News Overview Composition at Bloomberg. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 350–361, Online. Association for Computational Linguistics.