Large-scale Bilingual Language-Image Contrastive Learning
This paper is a technical report to share our experience and findings building a Korean and English bilingual multimodal model. While many of the multimodal datasets focus on English and multilingual multimodal research uses machine-translated texts, employing such machine-translated texts is limited to describing unique expressions, cultural information, and proper noun in languages other than English. In this work, we collect 1.1 billion image-text pairs (708 million Korean and 476 million English) and train a bilingual multimodal model named KELIP. We introduce simple yet effective training schemes, including MAE pre-training and multi-crop augmentation. Extensive experiments demonstrate that a model trained with such training schemes shows competitive performance in both languages. Moreover, we discuss multimodal-related research questions: 1) strong augmentation-based methods can distract the model from learning proper multimodal relations; 2) training multimodal model without cross-lingual relation can learn the relation via visual semantics; 3) our bilingual KELIP can capture cultural differences of visual semantics for the same meaning of words; 4) a large-scale multimodal model can be used for multimodal feature analogy. We hope that this work will provide helpful experience and findings for future research. We provide an open-source pre-trained KELIP.
Code (1)
Tasks
Contrastive LearningProper NounRelationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining
Vision-language foundation models like CLIP have revolutionized the field of artificial intelligence. Nevertheless, VLM models supporting multi-language, e.g., in both Chinese and English, have lagged due to the relative…
GPUzero-shot-classificationZero-Shot Cross-Modal RetrievalZero-shot Image Retrieval+3BilBOWA: Fast Bilingual Distributed Representations without Word Alignments
We introduce BilBOWA (Bilingual Bag-of-Words without Alignments), a simple and computationally-efficient model for learning bilingual distributed representations of words which can scale to large monolingual datasets and…
Cross-Lingual Document ClassificationDocument ClassificationGeneral ClassificationSentence+1FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model
Fine-grained vision-language understanding requires precise alignment between visual content and linguistic descriptions, a capability that remains limited in current models, particularly in non-English settings. While m…
Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capability
Large, multilingual language models exhibit surprisingly good zero- or few-shot machine translation capabilities, despite having never seen the intentionally-included translation examples provided to typical neural trans…
Language ModelingLanguage ModellingMachine TranslationTranslationMulti-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings
We introduce a novel suite of state-of-the-art bilingual text embedding models that are designed to support English and another target language. These models are capable of processing lengthy text inputs with up to 8192 …
Contrastive LearningMulti-Task LearningRetrievalSemantic Textual Similarity+2