Information Extraction with Character-level Neural Networks and Free Noisy Supervision

12/13/2016
by   Philipp Meerkamp, et al.
0

We present an architecture for information extraction from text that augments an existing parser with a character-level neural network. The network is trained using a measure of consistency of extracted data with existing databases as a form of noisy supervision. Our architecture combines the ability of constraint-based information extraction systems to easily incorporate domain knowledge and constraints with the ability of deep neural networks to leverage large amounts of data to learn complex features. Boosting the existing parser's precision, the system led to large improvements over a mature and highly tuned constraint-based production information extraction system used at Bloomberg for financial language text.

READ FULL TEXT
research
06/10/2014

FrameNet CNL: a Knowledge Representation and Information Extraction Language

The paper presents a FrameNet-based information extraction and knowledge...
research
06/04/2023

Does Character-level Information Always Improve DRS-based Semantic Parsing?

Even in the era of massive language models, it has been suggested that c...
research
11/06/2018

Parser Extraction of Triples in Unstructured Text

The web contains vast repositories of unstructured text. We investigate ...
research
09/12/2015

Improving distant supervision using inference learning

Distant supervision is a widely applied approach to automatic training o...
research
05/17/2013

Font Acknowledgment and Character Extraction of Digital and Scanned Images

The font recognition and character extraction is of immense importance a...
research
04/05/2016

RIGA at SemEval-2016 Task 8: Impact of Smatch Extensions and Character-Level Neural Translation on AMR Parsing Accuracy

Two extensions to the AMR smatch scoring script are presented. The first...
research
09/09/2014

Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures

Model-based methods and deep neural networks have both been tremendously...

Please sign up or login with your details

Forgot password? Click here to reset