| 1 |
Learning to scale multilingual representations for vision-language tasks
|
|
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Learning to scale multilingual representations for vision-language tasks
|
|
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Learning to Scale Multilingual Representations for Vision-Language Tasks ...
|
|
|
|
Abstract:
Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we propose a Scalable Multilingual Aligned Language Representation (SMALR) that supports many languages with few model parameters without sacrificing downstream task performance. SMALR learns a fixed size language-agnostic representation for most words in a multilingual vocabulary, keeping language-specific features for just a few. We use a masked cross-language modeling loss to align features with context from other languages. Additionally, we propose a cross-lingual consistency module that ensures predictions made for a query and its machine translation are comparable. The effectiveness of SMALR is demonstrated with ten diverse languages, over twice the number supported in vision-language tasks to date. We evaluate on multilingual image-sentence retrieval and outperform prior work by 3-4% with less than 1/5th ... : ECCV 2020 accepted spotlight paper ...
|
|
Keyword:
Computation and Language cs.CL; Computer Vision and Pattern Recognition cs.CV; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2004.04312
https://dx.doi.org/10.48550/arxiv.2004.04312
|
|
BASE
|
|
Hide details
|
|
|
| 4 |
Conversation Model Fine-Tuning for Classifying Client Utterances in Counseling Dialogues ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
