Naoki Murata
2024
On the Language Encoder of Contrastive Cross-modal Models
Mengjie Zhao
|
Junya Ono
|
Zhi Zhong
|
Chieh-Hsin Lai
|
Yuhta Takida
|
Naoki Murata
|
Wei-Hsiang Liao
|
Takashi Shibuya
|
Hiromi Wakaki
|
Yuki Mitsufuji
Findings of the Association for Computational Linguistics: ACL 2024
Contrastive cross-modal models such as CLIP and CLAP aid various vision-language (VL) and audio-language (AL) tasks. However, there has been limited investigation of and improvement in their language encoder – the central component of encoding natural language descriptions of image/audio into vector representations. We extensively evaluate how unsupervised and supervised sentence embedding training affect language encoder quality and cross-modal task performance. In VL pretraining, we found that sentence embedding training enhances language encoder quality and aids in cross-modal tasks, improving contrastive VL models such as CyCLIP. Sentence embedding training benefits AL tasks when the amount of training data is large. We analyze the representation spaces to understand the strengths of sentence embedding training, and find that it improves text-space uniformity, at the cost of decreased cross-modal alignment.
Search
Co-authors
- Mengjie Zhao 1
- Junya Ono 1
- Zhi Zhong 1
- Chieh-Hsin Lai 1
- Yuhta Takida 1
- show all...