Grounding learning of modifier dynamics: An application to color naming
Abstract
Grounding is crucial for natural language understanding. An important subtask is to understand modified color expressions, such as “light blue”. We present a model of color modifiers that, compared with previous additive models in RGB space, learns more complex transformations. In addition, we present a model that operates in the HSV color space. We show that certain adjectives are better modeled in that space. To account for all modifiers, we train a hard ensemble model that selects a color space depending on the modifier-color pair. Experimental results show significant and consistent improvements compared to the state-of-the-art baseline model.- Anthology ID:
- D19-1158
- Volume:
- Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Editors:
- Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
- Venues:
- EMNLP | IJCNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1488–1493
- Language:
- URL:
- https://aclanthology.org/D19-1158
- DOI:
- 10.18653/v1/D19-1158
- Cite (ACL):
- Xudong Han, Philip Schulz, and Trevor Cohn. 2019. Grounding learning of modifier dynamics: An application to color naming. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1488–1493, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Grounding learning of modifier dynamics: An application to color naming (Han et al., EMNLP-IJCNLP 2019)
- PDF:
- https://preview.aclanthology.org/teach-a-man-to-fish/D19-1158.pdf
- Code
- HanXudong/GLoM