Task Grouping for Multilingual Text Recognition
Most existing OCR methods focus on alphanumeric characters due to the popularity of English and numbers, as well as their corresponding datasets. On extending the characters to more languages, recent methods have shown that training different scripts with different recognition heads can greatly improve the end-to-end recognition accuracy compared to combining characters from all languages in the same recognition head. However, we postulate that similarities between some languages could allow sharing of model parameters and benefit from joint training. Determining language groupings, however, is not immediately obvious. To this end, we propose an automatic method for multilingual text recognition with a task grouping and assignment module using Gumbel-Softmax, introducing a task grouping loss and weighted recognition loss to allow for simultaneous training of the models and grouping modules. Experiments on MLT19 lend evidence to our hypothesis that there is a middle ground between combining every task together and separating every task that achieves a better configuration of task grouping/separation.
Code (1)
Tasks
Optical Character Recognition (OCR)Similar Papers 제목 키워드 기반
Language Clustering for Multilingual Named Entity Recognition
Recent work in multilingual natural language processing has shown progress in various tasks such as natural language inference and joint multilingual translation. Despite success in learning across many languages, challe…
ClusteringLanguage IdentificationLanguage ModelingLanguage Modelling+7GradSim: Gradient-Based Language Grouping for Effective Multilingual Training
Most languages of the world pose low-resource challenges to natural language processing models. With multilingual training, knowledge can be shared among languages. However, not all languages positively influence each ot…
Sentiment AnalysisGroup Activity Recognition Using Joint Learning of Individual Action Recognition and People Grouping
This paper proposes joint learning of individual action recognition and people grouping for improving group activity recognition. By sharing the information between two similar tasks (i.e., individual action recognition …
Action RecognitionActivity RecognitionGroup Activity RecognitionGroupViT: Semantic Segmentation Emerges from Text Supervision
Grouping and recognition are important components of visual scene understanding, e.g., for object detection and semantic segmentation. With end-to-end deep learning systems, grouping of image regions usually happens impl…
Object DetectionScene UnderstandingSemantic SegmentationTransfer Learning+1German Text Embedding Clustering Benchmark
This work introduces a benchmark assessing the performance of clustering German text embeddings in different domains. This benchmark is driven by the increasing use of clustering neural text embeddings in tasks that requ…
BenchmarkingClustering