2019
EMNLP
EMNLP 2019
IMSurReal: IMS at the Surface Realization Shared Task 2019
Abstract
AbstractWe introduce the IMS contribution to the Surface Realization Shared Task 2019. Our submission achieves the state-of-the-art performance without using any external resources. The system takes a pipeline approach consisting of five steps: linearization, completion, inflection, contraction, and detokenization. We compare the performance of our linearization algorithm with two external baselines and report results for each step in the pipeline. Furthermore, we perform detailed error analysis revealing correlation between word order freedom and difficulty of the linearization task.
🌉
Interdisciplinary Bridge
— Computer Science and Natural Language Processing
📈
Trend Setter
— Natural Language Generation
🧭
Keyword Pioneer
— linearization algorithms
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Interdisciplinary, Machine Learning, Mathematics & Optimization, Natural Language Processing