Stefan Riezler

NLmaps: A Natural Language Interface to Query OpenStreetMap.

2016 · International Conference on Computational Linguistics

We present a Natural Language Interface (nlmaps.cl.uni-heidelberg.de) to query OpenStreetMap. Natural language questions about geographical facts are parsed into database queries that can be executed against the OpenStreetMap (OSM) database. After parsing the question, the …

Correct Me If You Can: Learning from Error Corrections and Markings

2020 · arXiv (Cornell University)

Sequence-to-sequence learning involves a trade-off between signal strength and annotation cost of training data. For example, machine translation data range from costly expert-generated translations that enable supervised learning, to weak quality-judgment feedback that facilitate reinforcement …