Andreas Madsack


2019

pdf bib
AX Semantics’ Submission to the SIGMORPHON 2019 Shared Task
Andreas Madsack | Robert Weißgraeber
Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology

This paper describes the AX Semantics’ submission to the SIGMORPHON 2019 shared task on morphological reinflection. We implemented two systems, both tackling the task for all languages in one codebase, without any underlying language specific features. The first one is an encoder-decoder model using AllenNLP; the second system uses the same model modified by a custom trainer that trains only with the target language resources after a specific threshold. We especially focused on building an implementation using AllenNLP with out-of-the-box methods to facilitate easy operation and reuse.

2018

pdf bib
AX Semantics’ Submission to the CoNLLSIGMORPHON 2018 Shared Task
Andreas Madsack | Alessia Cavallo | Johanna Heininger | Robert Weißgraeber
Proceedings of the CoNLL–SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection

pdf bib
AX Semantics’ Submission to the Surface Realization Shared Task 2018
Andreas Madsack | Johanna Heininger | Nyamsuren Davaasambuu | Vitaliia Voronik | Michael Käufl | Robert Weißgraeber
Proceedings of the First Workshop on Multilingual Surface Realisation

In this paper we describe our system and experimental results on the development set of the Surface Realisation Shared Task. Our system is an entry for the Shallow-Task, with two different models based on deep-learning implementations for building the sentence combined with a rule-based morphology component.

pdf bib
Multi-Language Surface Realisation as REST API based NLG Microservice
Andreas Madsack | Johanna Heininger | Nyamsuren Davaasambuu | Vitaliia Voronik | Michael Käufl | Robert Weißgraeber
Proceedings of the 11th International Conference on Natural Language Generation

We present a readily available API that solves the morphology component for surface realizers in 10 languages (e.g., English, German and Finnish) for any topic and is available as REST API. This can be used to add morphology to any kind of NLG application (e.g., a multi-language chatbot), without requiring computational linguistic knowledge by the integrator.

2017

pdf bib
A working, non-trivial, topically indifferent NLG System for 17 languages
Robert Weißgraeber | Andreas Madsack
Proceedings of the 10th International Conference on Natural Language Generation

A fully fledged practical working application for a rule-based NLG system is presented that is able to create non-trivial, human sounding narrative from structured data, in any language and for any topic.