1 Hit in 5.4 sec

Thomson Reuters' Submission to the FEIII 2017 Challenge Non-scored Tasks

Elizabeth Roman, Brian Ulicny, Yilun Du, Srijith Poduval, Allan Ko
2017 Proceedings of the 3rd International Workshop on Data Science for Macro--Modeling with Financial and Economic Datasets - DSMM'17  
In this paper we describe a machine learning approach to predict roles of extracted SEC triples for the non-scored task of the 2017 FEIII Challenge.  ...  INTRODUCTION e main task of the FEIII 2017 challenge [1] was to predict the relevance of triples extracted from 10-K and 10-Q SEC lings. e provided datasets containing the following information for a  ...  Table 1 shows the 10 role types and their descriptions. e non-scored tasks then asked us to consider additional tasks built on top of the initial task: 1) apply NLP and Machine Learning to further embellish  ... 
doi:10.1145/3077240.3077244 dblp:conf/sigmod/RomanUDPK17a fatcat:udtujvy45bhuhdq5jfyaunw4ye