DeRE

A novel framework for declarative specification and compilation of template-based information extraction

DeRE

Type
Tool
Author
Heike Adel, Laura Bostan, Sean Papay, Sebastian Padó, Roman Klinger
Description

Most machine learning systems for natural language processing are tailored to specific tasks. As a result, comparability of models across tasks is missing and their applicability to new tasks is limited. This affects end users without machine learning experience as well as model developers. To address these limitations, we present DeRE, a novel framework for declarative specification and compilation of template-based information extraction.

DeRE uses a generic specification language for the task and for data annotations in terms of spans and frames. This formalism enables the representation of a large variety of natural language processing challenges. The backend can be instantiated by different models, following different paradigms. The clear separation of frame specification and model backend will ease the implementation of new models and the evaluation of different models across different tasks. Furthermore, it simplifies transfer learning, joint learning across tasks and/or domains as well as the assessment of model generalizability.

Reference

Heike Adel, Laura Bostan, Sean Papay, Sebastian Padó, Roman Klinger: "DeRE: A Task and Domain-Independent Slot Filling Framework for Declarative Relation Extraction". EMNLP 2018. System Demonstrations.

Download
This image shows Sebastian Padó

Sebastian Padó

Prof. Dr.

Chair of Theoretical Computational Linguistics, Managing Director of the IMS

This image shows Roman Klinger

Roman Klinger

Prof. Dr.

Adjunct Professor

To the top of the page