Publication
COLING 2020
Conference paper

Identifying Motion Entities in Natural Language and A Case Study for Named Entity Recognition

Download paper

Abstract

Motion recognition is one of the basic cognitive capabilities of many life forms, however, detecting and understanding motion in text is not a trivial task. In addition, identifying motion entities in natural language is not only challenging but also beneficial for a better natural language understanding. In this paper, we present a Motion Entity Tagging model to identify entities in motion in a text, along with the Literal-Motion-in-Text (LiMiT) dataset used for training the model. We also present results showing that motion features, in particular, entity in motion benefits the Named-Entity Recognition (NER) task. Finally, we present an analysis for the special co-occurrence relation between the person category in NER and animate entities in motion, which significantly improves the classification performance for the person category in NER.

Date

Publication

COLING 2020

Authors

Topics

Resources

Share