Named entity recognition from financial press releases

Rebecca J. Passonneau, Tifara Ramelson, Boyi Xie

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper explores a previous model’s use of named entity recognition to predict the changes in stock prices from financial news. Detecting company mentions in the articles is crucial for this task, and we modified these methods to gain additional mentions. We first expanded upon the rules of the named entity recognition from the original model. We also incorporated coreference resolution and modified an existing toolkit to be compatible with our specific domain. After these two adjustments, the number of instances captured increased significantly. Although this did not necessarily improve the overall prediction performance, the results give us an opportunity to explore reasons why the scores stayed around the same, and a full analysis will allow us to achieve our goals.

Original languageEnglish (US)
Title of host publicationKnowledge Discovery, Knowledge Engineering and Knowledge Management - 6th International Joint Conference, IC3K 2014, Revised Selected Papers
EditorsJoaquim Filipe, Jan L.G. Dietz, Joaquim Filipe, Jan L.G. Dietz, Kecheng Liu, David Aveiro, Ana Fred, David Aveiro, Ana Fred, Kecheng Liu
PublisherSpringer Verlag
Pages240-254
Number of pages15
ISBN (Print)9783319258393, 9783319258393
DOIs
StatePublished - Jan 1 2015
Event6th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2014 - Rome, Italy
Duration: Oct 21 2014Oct 24 2014

Publication series

NameCommunications in Computer and Information Science
Volume553
ISSN (Print)1865-0929

Other

Other6th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2014
CountryItaly
CityRome
Period10/21/1410/24/14

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Mathematics(all)

Fingerprint Dive into the research topics of 'Named entity recognition from financial press releases'. Together they form a unique fingerprint.

Cite this