Abstract
Learned dynamic weighting of the conditioning signal (attention) has been shown to improve neural language generation in a variety of settings. The weights applied when generating a particular output sequence have also been viewed as providing a potentially explanatory insight in the internal workings of the generator. In this paper, we reverse the direction of this connection and ask whether through the control of the attention of the model we can control its output. Specifically, we take a standard neural image captioning model that uses attention, and fix the attention to predetermined areas in the image. We evaluate whether the resulting output is more likely to mention the class of the object in that area than the normally generated caption. We introduce three effective methods to control the attention and find that these are producing expected results in up to 27.43% of the cases.- Anthology ID:
- W19-8653
- Volume:
- Proceedings of the 12th International Conference on Natural Language Generation
- Month:
- October–November
- Year:
- 2019
- Address:
- Tokyo, Japan
- Editors:
- Kees van Deemter, Chenghua Lin, Hiroya Takamura
- Venue:
- INLG
- SIG:
- SIGGEN
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 427–431
- Language:
- URL:
- https://aclanthology.org/W19-8653
- DOI:
- 10.18653/v1/W19-8653
- Cite (ACL):
- Philipp Sadler, Tatjana Scheffler, and David Schlangen. 2019. Can Neural Image Captioning be Controlled via Forced Attention?. In Proceedings of the 12th International Conference on Natural Language Generation, pages 427–431, Tokyo, Japan. Association for Computational Linguistics.
- Cite (Informal):
- Can Neural Image Captioning be Controlled via Forced Attention? (Sadler et al., INLG 2019)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/W19-8653.pdf
- Data
- MS COCO, Visual Genome