论文阅读---REALISE model

REALISE model:

1.utilizes multiple encoders to obtain the semantic ,phonetic , and graphic information to distinguish the similarities of Chinese characters and correct the spelling errors.

2.And then, develop a selective modality fusion module to obtain the context-aware multimodal representations.

3.Finally ,the output layer predict the probabilities of error corrections.

Encoders:

Semantic encoder:

BERT, which provides rich contextual word representation with the unsupervised pretraining on large corpora.

复制代码
from transformers import BertTokenizer
tokenizer = BertTokenizer.from_pretrained('bert-base-chinese')

Tokenizer是一种文本处理工具,用于将文本分解成单个单词(称为tokens)或其他类型的单位,例如标点符号和数字。在自然语言处理领域,tokenizer通常用于将句子分解为单个单词或词元,以便进行文本分析和机器学习任务。常用的tokenizer包括基于规则的tokenizer和基于机器学习的tokenizer,其中基于机器学习的tokenizer可以自动识别单词和短语的边界,并将其分解为单个tokens。

Phonetic encoder

pinyin: initial(21)+final(39)+tone(5)

hierarchical phonetic encoder :character-level encoder and sentence-level encoder

Character-level encoder

GRU:

GRU(Gate Recurrent Unit)是循环神经网络(Recurrent Neural Network, RNN)的一种。和LSTM(Long-Short Term Memory)一样,也是为了解决长期记忆和反向传播中的梯度等问题而提出来的。

GRU和LSTM在很多情况下实际表现上相差无几,那么为什么我们要使用新人GRU(2014年提出)而不是相对经受了更多考验的LSTM(1997提出)呢。
我们在我们的实验中选择GRU是因为它的实验效果与LSTM相似,但是更易于计算。

Sentence-level Encoder: obtain the contextualized phonetic representation for each Chinese characters

4-layer Transformer with the same hidden size as the semantic encoder

because independent phonetic vectors are not distinguished in order, so we add the positional embeading to each vector. +pack the vector together ->transformer layers to calculate the contextualized representation in acoustic modality.

Graphic Encoder

ResNet

three fonds correpond to the three channels of the character images whose size is set to 32*32 pixel

Selective Modality Fusion Module

Ht, Ha,Hv ==textual ,acoustic,visual

fuse information i n different modalities

selective gate unit: select how much information flow to the mixed multimodal representation.

gate values :fully-connected layer followed by a sigmoid function.

Acoustic and Visual Pretraining

aims to learn the acoustic-textual and visual-textual relationships

phonetic encoder:input method pretraining objective

graphhic encoder:OCP pretraining objective

Data and Metrics

data:SIGHAN --->convert to simplified chinese by using the OPENCC tools

two level :detection and correction level to test the model

相关推荐
王上上1 小时前
【论文阅读30】Bi-LSTM(2024)
论文阅读·人工智能·lstm
qq_416276421 小时前
作为点的对象CenterNet论文阅读
论文阅读
写代码的小阿帆10 小时前
Fractal Generative Models论文阅读笔记与代码分析
论文阅读·stable diffusion·transformer
王上上10 小时前
【论文阅读29】区间预测CIPM(2025)
论文阅读
Matrix_1110 小时前
论文阅读:Matting by Generation
论文阅读·人工智能·计算摄影
王上上13 小时前
【论文阅读28】-CNN-BiLSTM-Attention-(2024)
论文阅读·人工智能·cnn
大写-凌祁1 天前
论文阅读:HySCDG生成式数据处理流程
论文阅读·人工智能·笔记·python·机器学习
颜妮儿1 天前
论文笔记——相干体技术在裂缝预测中的应用研究
论文阅读
柠石榴1 天前
【论文阅读笔记】《A survey on deep learning approaches for text-to-SQL》
论文阅读·笔记·深度学习·nlp·text-to-sql
张较瘦_1 天前
[论文阅读] 人工智能 | 搜索增强LLMs的用户偏好与性能分析
论文阅读·人工智能