Efficient Character-level Document Classification by Combining Convolution and Recurrent Layers
Document classification tasks were primarily tackled at word level. Recent research that works with character-level inputs shows several benefits over word-level approaches such as natural incorporation of morphemes and better handling of rare words. We propose a neural network architecture that utilizes both convolution and recurrent layers to efficiently encode character inputs. We validate the proposed model on eight large scale document classification tasks and compare with character-level convolution-only models. It achieves comparable performances with much less parameters.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationDocument ClassificationGeneral ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Document Image Classification with Intra-Domain Transfer Learning and Stacked Generalization of Deep Convolutional Neural Networks
In this work, a region-based Deep Convolutional Neural Network framework is proposed for document structure learning. The contribution of this work involves efficient training of region based classifiers and effective en…
document-image-classificationDocument Image ClassificationGeneral Classificationimage-classification+2Utilizing Visual Forms of Japanese Characters for Neural Review Classification
We propose a novel method that exploits visual information of ideograms and logograms in analyzing Japanese review documents. Our method first converts font images of Japanese characters into character embeddings using c…
ClassificationGeneral ClassificationSentenceBidirectional Convolutional Poisson Gamma Dynamical Systems
Incorporating the natural document-sentence-word structure into hierarchical Bayesian modeling, we propose convolutional Poisson gamma dynamical systems (PGDS) that introduce not only word-level probabilistic convolution…
Bayesian InferenceSentenceVariational InferencePage Stream Segmentation with Convolutional Neural Nets Combining Textual and Visual Features
In recent years, (retro-)digitizing paper-based files became a major undertaking for private and public archives as well as an important task in electronic mailroom applications. As a first step, the workflow involves sc…
Optical Character RecognitionOptical Character Recognition (OCR)Page Stream SegmentationEnd-to-End Text Classification via Image-based Embedding using Character-level Networks
For analysing and/or understanding languages having no word boundaries based on morphological analysis such as Japanese, Chinese, and Thai, it is desirable to perform appropriate word segmentation before word embeddings.…
Document ClassificationGeneral ClassificationMorphological Analysistext-classification+2