Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCross-lingual Cross-modal Pretraining for Multimodal Retrieval
تبادل اللغات التعليب الوسائط الاحتجاج لاسترجاع الوسائط المتعددة
229
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
حققت نماذج لغة الرؤية المحددة الأخيرة أداء مثير للإعجاب على مهام الاسترجاع عبر مشروط باللغة الإنجليزية. ومع ذلك، تعتمد نجاحهم بشكل كبير على توافر العديد من مجموعات بيانات التعليق المشروح على الصورة لإحاطاء، حيث لا تكون النصوص بالضرورة باللغة الإنجليزية. على الرغم من أنه يمكننا استخدام أدوات الترجمة الآلية (MT) لترجمة النص غير الإنجليزي إلى اللغة الإنجليزية، فإن الأداء لا يزال يعتمد إلى حد كبير على جودة MT وقد يعاني من مشاكل عالية من الكمون في تطبيقات العالم الحقيقي. تقترح هذه الورقة نهجا جديدا لتعلم تمثيلات متعددة الوسائط عبر اللغات لمطابقة الصور وإياراتها ذات الصلة بلغات متعددة. نجمع بسلاسة بسلاسة أهداف محالمانية عبر اللغات وأهداف محالم الاحتجاج بالعدوان في إطار موحد لتعلم الصور والنص في مساحة تضمين مشتركة من بيانات التسمية التوضيحية باللغة الإنجليزية المتاحة، مونولينغيا ومتوازي Corpus. نظظ أن نهجنا يحقق أداء SOTA في مهام استرجاع على معايير التسمية التوضيحية متعددة اللغات متعددة اللغات متعددة اللغات: multi30k مع التسميات التوضيحية الألمانية و mscoco مع التسميات التوضيحية اليابانية.
Recent pretrained vision-language models have achieved impressive performance on cross-modal retrieval tasks in English. Their success, however, heavily depends on the availability of many annotated image-caption datasets for pretraining, where the texts are not necessarily in English. Although we can utilize machine translation (MT) tools to translate non-English text to English, the performance still largely relies on MT's quality and may suffer from high latency problems in real-world applications. This paper proposes a new approach to learn cross-lingual cross-modal representations for matching images and their relevant captions in multiple languages. We seamlessly combine cross-lingual pretraining objectives and cross-modal pretraining objectives in a unified framework to learn image and text in a joint embedding space from available English image-caption data, monolingual and parallel corpus. We show that our approach achieves SOTA performance in retrieval tasks on two multimodal multilingual image caption benchmarks: Multi30k with German captions and MSCOCO with Japanese captions.
References used
https://aclanthology.org/
rate research
Read More
Recent advances in using retrieval components over external knowledge sources have shown impressive results for a variety of downstream tasks in natural language processing. Here, we explore the use of unstructured external knowledge sources of image
s and their corresponding captions for improving visual question answering (VQA). First, we train a novel alignment model for embedding images and captions in the same space, which achieves substantial improvement in performance on image-caption retrieval w.r.t. similar methods. Second, we show that retrieval-augmented multi-modal transformers using the trained alignment model improve results on VQA over strong baselines. We further conduct extensive experiments to establish the promise of this approach, and examine novel applications for inference time such as hot-swapping indices.
This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically, we focus on multilingual text-to-video search and propose a Transformer-based model that learns contextual multilingual multimodal embeddings. Under a zero-s
hot setting, we empirically demonstrate that performance degrades significantly when we query the multilingual text-video model with non-English sentences. To address this problem, we introduce a multilingual multimodal pre-training strategy, and collect a new multilingual instructional video dataset (Multi-HowTo100M) for pre-training. Experiments on VTT show that our method significantly improves video search in non-English languages without additional annotations. Furthermore, when multilingual annotations are available, our method outperforms recent baselines by a large margin in multilingual text-to-video search on VTT and VATEX; as well as in multilingual text-to-image search on Multi30K. Our model and Multi-HowTo100M is available at http://github.com/berniebear/Multi-HT100M.
Dense retrieval has shown great success for passage ranking in English. However, its effectiveness for non-English languages remains unexplored due to limitation in training resources. In this work, we explore different transfer techniques for docume
nt ranking from English annotations to non-English languages. Our experiments reveal that zero-shot model-based transfer using mBERT improves search quality. We find that weakly-supervised target language transfer is competitive compared to generation-based target language transfer, which requires translation models.
We propose a new task, Text2Mol, to retrieve molecules using natural language descriptions as queries. Natural language and molecules encode information in very different ways, which leads to the exciting but challenging problem of integrating these
two very different modalities. Although some work has been done on text-based retrieval and structure-based retrieval, this new task requires integrating molecules and natural language more directly. Moreover, this can be viewed as an especially challenging cross-lingual retrieval problem by considering the molecules as a language with a very unique grammar. We construct a paired dataset of molecules and their corresponding text descriptions, which we use to learn an aligned common semantic embedding space for retrieval. We extend this to create a cross-modal attention-based model for explainability and reranking by interpreting the attentions as association rules. We also employ an ensemble approach to integrate our different architectures, which significantly improves results from 0.372 to 0.499 MRR. This new multimodal approach opens a new perspective on solving problems in chemistry literature understanding and molecular machine learning.
Aspect terms extraction (ATE) and aspect sentiment classification (ASC) are two fundamental and fine-grained sub-tasks in aspect-level sentiment analysis (ALSA). In the textual analysis, joint extracting both aspect terms and sentiment polarities has
been drawn much attention due to the better applications than individual sub-task. However, in the multi-modal scenario, the existing studies are limited to handle each sub-task independently, which fails to model the innate connection between the above two objectives and ignores the better applications. Therefore, in this paper, we are the first to jointly perform multi-modal ATE (MATE) and multi-modal ASC (MASC), and we propose a multi-modal joint learning approach with auxiliary cross-modal relation detection for multi-modal aspect-level sentiment analysis (MALSA). Specifically, we first build an auxiliary text-image relation detection module to control the proper exploitation of visual information. Second, we adopt the hierarchical framework to bridge the multi-modal connection between MATE and MASC, as well as separately visual guiding for each sub module. Finally, we can obtain all aspect-level sentiment polarities dependent on the jointly extracted specific aspects. Extensive experiments show the effectiveness of our approach against the joint textual approaches, pipeline and collapsed multi-modal approaches.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
