Search Results for author:
Found 7 papers, 2 papers with code
融入多尺度特征注意力的胶囊神经网络及其在文本分类中的应用(Incorporating Multi-scale Feature Attention into Capsule Network and its Application in Text Classification)
近些年来, 胶囊神经网络(Capsnets)由于拥有强大的文本特征学习能力已被应用到了文本分类任务当中。目前的研究工作大部分都将提取到的文本多元语法特征视为同等重要, 而忽略了单词所对应各个多元语法特征的重要程度应该是由具体上下文决定的这一问题, 这将直接影响到模型对整个文本的语义理解。针对上述问题, 本文提出了多尺度特征部分连接胶囊网络(MulPart-Capsnets)。该方法将多尺度特征注意力融入到Capsnets中, 多尺度特征注意力能够自动选择不同尺度的多元语法特征, 通过对其进行加权求和, 就能为每个单词精确捕捉到丰富的多元语法特征。同时, 为了减少子胶囊与父胶囊之间的冗余信息传递, 本文同时也对路由算法进行了改进。 本文提出的算法在文本分类任务上针对七个著名的数据集进行了有效性验证, 和现有的研究工作相比, 性能显著提高, 说明了本文的算法能够捕获文本中更丰富的多元语法特征, 具有更加强大的文本特征学习能力。
Automatic Word Segmentation and Part-of-Speech Tagging of Ancient Chinese Based on BERT Model
In recent years, new deep learning methods and pre-training language models have been emerging in the field of natural language processing (NLP).
Chatbots in Knowledge-Intensive Contexts: Comparing Intent and LLM-Based Systems
Cognitive assistants (CA) are chatbots that provide context-aware support to human workers in knowledge-intensive tasks.
Knowledge Sharing in Manufacturing using Large Language Models: User Evaluation and Model Benchmarking
This paper introduces a Large Language Model (LLM)-based system designed to retrieve information from the extensive knowledge contained in factory documentation and knowledge shared by expert operators.
Heterogeneous Graph Tree Networks
Heterogeneous graph neural networks (HGNNs) have attracted increasing research interest in recent three years.
GTNet: A Tree-Based Deep Graph Learning Architecture
We formulate a general propagation rule following the nature of message passing in the tree to update a node's feature by aggregating its initial feature and its neighbor nodes' updated features.
Ranked #49 on
Node Property Prediction
on ogbn-arxiv
