اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدGlyphCRM: Bidirectional Encoder Representation for Chinese Character with its Glyph
80
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Previous works indicate that the glyph of Chinese characters contains rich semantic information and has the potential to enhance the representation of Chinese characters. The typical method to utilize the glyph features is by incorporating them into the character embedding space. Inspired by previous methods, we innovatively propose a Chinese pre-trained representation model named as GlyphCRM, which abandons the ID-based character embedding method yet solely based on sequential character images. We render each character into a binary grayscale image and design two-channel position feature maps for it. Formally, we first design a two-layer residual convolutional neural network, namely HanGlyph to generate the initial glyph representation of Chinese characters, and subsequently adopt multiple bidirectional encoder Transformer blocks as the superstructure to capture the context-sensitive information. Meanwhile, we feed the glyph features extracted from each layer of the HanGlyph module into the underlying Transformer blocks by skip-connection method to fully exploit the glyph features of Chinese characters. As the HanGlyph module can obtain a sufficient glyph representation of any Chinese character, the long-standing out-of-vocabulary problem could be effectively solved. Extensive experimental results indicate that GlyphCRM substantially outperforms the previous BERT-based state-of-the-art model on 9 fine-tuning tasks, and it has strong transferability and generalization on specialized fields and low-resource tasks. We hope this work could spark further research beyond the realms of well-established representation of Chinese texts.
قيم البحث
اقرأ أيضاً
Single online handwritten Chinese character recognition~(single OLHCCR) has achieved prominent performance. However, in real application scenarios, users always write multiple Chinese characters to form one complete sentence and the contextual inform
ation within these characters holds the significant potential to improve the accuracy, robustness and efficiency of sentence-level OLHCCR. In this work, we first propose a simple and straightforward end-to-end network, namely vanilla compositional network~(VCN) to tackle the sentence-level OLHCCR. It couples convolutional neural network with sequence modeling architecture to exploit the handwritten characters previous contextual information. Although VCN performs much better than the state-of-the-art single OLHCCR model, it exposes high fragility when confronting with not well written characters such as sloppy writing, missing or broken strokes. To improve the robustness of sentence-level OLHCCR, we further propose a novel deep spatial-temporal fusion network~(DSTFN). It utilizes a pre-trained autoregresssive framework as the backbone component, which projects each Chinese character into word embeddings, and integrates the spatial glyph features of handwritten characters and their contextual information multiple times at multi-layer fusion module. We also construct a large-scale sentence-level handwriting dataset, named as CSOHD to evaluate models. Extensive experiment results demonstrate that DSTFN achieves the state-of-the-art performance, which presents strong robustness compared with VCN and exiting single OLHCCR models. The in-depth empirical analysis and case studies indicate that DSTFN can significantly improve the efficiency of handwriting input, with the handwritten Chinese character with incomplete strokes being recognized precisely.
Given the advantage and recent success of English character-level and subword-unit models in several NLP tasks, we consider the equivalent modeling problem for Chinese. Chinese script is logographic and many Chinese logograms are composed of common s
ubstructures that provide semantic, phonetic and syntactic hints. In this work, we propose to explicitly incorporate the visual appearance of a characters glyph in its representation, resulting in a novel glyph-aware embedding of Chinese characters. Being inspired by the success of convolutional neural networks in computer vision, we use them to incorporate the spatio-structural patterns of Chinese glyphs as rendered in raw pixels. In the context of two basic Chinese NLP tasks of language modeling and word segmentation, the model learns to represent each characters task-relevant semantic and syntactic information in the character-level embedding.
In this paper, we present a novel implicit glyph shape representation, which models glyphs as shape primitives enclosed by quadratic curves, and naturally enables generating glyph images at arbitrary high resolutions. Experiments on font reconstructi
on and interpolation tasks verified that this structured implicit representation is suitable for describing both structure and style features of glyphs. Furthermore, based on the proposed representation, we design a simple yet effective disentangled network for the challenging one-shot font style transfer problem, and achieve the best results comparing to state-of-the-art alternatives in both quantitative and qualitative comparisons. Benefit from this representation, our generated glyphs have the potential to be converted to vector fonts through post-processing, reducing the gap between rasterized images and vector graphics. We hope this work can provide a powerful tool for 2D shape analysis and synthesis, and inspire further exploitation in implicit representations for 2D shape modeling.
Embedding entities and relations into a continuous multi-dimensional vector space have become the dominant method for knowledge graph embedding in representation learning. However, most existing models ignore to represent hierarchical knowledge, such
as the similarities and dissimilarities of entities in one domain. We proposed to learn a Domain Representations over existing knowledge graph embedding models, such that entities that have similar attributes are organized into the same domain. Such hierarchical knowledge of domains can give further evidence in link prediction. Experimental results show that domain embeddings give a significant improvement over the most recent state-of-art baseline knowledge graph embedding models.
Characterizing users interests accurately plays a significant role in an effective recommender system. The sequential recommender system can learn powerful hidden representations of users from successive user-item interactions and dynamic users prefe
rences. To analyze such sequential data, conventional methods mainly include Markov Chains (MCs) and Recurrent Neural Networks (RNNs). Recently, the use of self-attention mechanisms and bi-directional architectures have gained much attention. However, there still exists a major limitation in previous works that they only model the users main purposes in the behavioral sequences separately and locally, and they lack the global representation of the users whole sequential behavior. To address this limitation, we propose a novel bidirectional sequential recommendation algorithm that integrates the users local purposes with the global preference by additive supervision of the matching task. We combine the mask task with the matching task in the training process of the bidirectional encoder. A new sample production method is also introduced to alleviate the effect of mask noise. Our proposed model can not only learn bidirectional semantics from users behavioral sequences but also explicitly produces user representations to capture users global preference. Extensive empirical studies demonstrate our approach considerably outperforms various state-of-the-art models.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
