Search Results for author:
Found 37 papers, 8 papers with code
基于枢轴语言系统融合的词汇混淆网络神经机器翻译(Neural Machine Translation for Vocabulary Confusion Network Based on Pivotal Language System Fusion)
“神经机器翻译在低资源语言的翻译任务中存在翻译难度大、译文质量不佳的问题。本文针对低资源语言与汉语之间没有双语平行语料的情况, 采用正反向枢轴翻译的方法, 生成了三种低资源语言到汉语的平行句对, 采用词汇级的系统融合技术, 将Transformer模型和对偶学习模型翻译生成的目标语言译文进行融合, 然后通过混淆神经网络进行词汇选择, 生成了更为优质的目标语言译文。实验证明, 本文提出的多模型融合方法在爱沙尼亚语-汉语、拉脱维亚语-汉语、罗马尼亚语-汉语这三种低资源语言翻译任务中均优于独立模型的翻译效果, 进一步提升了低资源语言神经机器翻译的译文质量。”
Question Generation Based on Grammar Knowledge and Fine-grained Classification
Then, the types predicted by the question type classifier are fed into the question generator.
JCapsR: 一种联合胶囊神经网络的藏语知识图谱表示学习模型(JCapsR: A Joint Capsule Neural Network for Tibetan Knowledge Graph Representation Learning)
“知识图谱表示学习是自然语言处理的一项关键技术, 现有的知识图谱表示研究主要集中在英语、汉语等语言, 而低资源语言的知识图谱表示学习研究还处于探索阶段, 例如藏语。本文基于前期构建的藏语知识图谱, 提出了一种联合胶囊神经网络(JCapsR)的藏语知识图谱表示学习模型。首先, 我们使用TransR模型生成藏语知识图谱的结构化信息表示。其次, 采用融合多头注意力和关系注意力的Transformer模型表示藏语实体的文本描述信息。最后, 采用JCapsR进一步提取三元组在知识图谱语义空间中的关系, 将实体文本描述信息和结构化信息融合, 得到藏语知识图谱的表示。实验结果表明, 相比基线系统, 联合胶囊神经网络JCapsR模型提高了藏语知识图谱表示学习的效果, 相关研究为其它低资源语言知识图谱表示学习的拓展优化提供了参考借鉴意义。”
Ti-Reader: 基于注意力机制的藏文机器阅读理解端到端网络模型(Ti-Reader: An End-to-End Network Model Based on Attention Mechanisms for Tibetan Machine Reading Comprehension)
“机器阅读理解旨在教会机器去理解一篇文章并且回答与之相关的问题。为了解决低资源语言上机器阅读理解模型性能低的问题, 本文提出了一种基于注意力机制的藏文机器阅读理解端到端网络模型Ti-Reader。首先, 为了编码更细粒度的藏文文本信息, 本文将音节和词相结合进行词表示, 然后采用词级注意力机制去关注文本中的关键词, 采用重读机制去捕捉文章和问题之间的语义信息, 采用自注意力机制去匹配问题与答案的隐变量本身, 为答案预测提供更多的线索。最后, 实验结果表明, Ti-Reader模型提升了藏文机器阅读理解的性能, 并且在英文数据集SQuAD上也有较好的表现。”
面向机器阅读理解的高质量藏语数据集构建(Construction of High-quality Tibetan Dataset for Machine Reading Comprehension)
“机器阅读理解是通过算法让机器根据给定的上下文回答问题, 从而测试机器理解自然语言的程度。其中, 数据集的构建是机器阅读理解的主要任务。目前, 相关算法模型在大多数流行的英语数据集上都取得了显著的成绩, 甚至超过了人类的表现。但对于低资源语言, 由于缺乏相应的数据集, 机器阅读理解研究还处于起步阶段。本文以藏语为例, 人工构建了藏语机器阅读理解数据集(TibetanQA), 其中包含20000个问题答案对和1513篇文章。本数据集的文章均来自云藏网, 涵盖了自然、文化和教育等12个领域的知识, 问题形式多样且具有一定的难度。另外, 该数据集在文章收集、问题构建、答案验证、回答多样性和推理能力等方面, 均采用严格的流程以确保数据的质量, 同时采用基于语言特征消融输入的验证方法说明了数据集的质量。最后, 本文初步探索了三种经典的英语阅读理解模型在TibetanQA数据集上的表现, 其结果难以媲美人类, 这表明在藏语机器阅读理解任务上还需要更进一步的探索。”
DHRNet: A Dual-Path Hierarchical Relation Network for Multi-Person Pose Estimation
Multi-person pose estimation (MPPE) presents a formidable yet crucial challenge in computer vision.
Evolutionary Multi-Objective Optimisation for Fairness-Aware Self Adjusting Memory Classifiers in Data Streams
This paper introduces a novel approach, evolutionary multi-objective optimisation for fairness-aware self-adjusting memory classifiers, designed to enhance fairness in machine learning algorithms applied to data stream classification.
Genetic-based Constraint Programming for Resource Constrained Job Scheduling
In the proposed algorithm, evolved programs represent variable selectors to be used in the search process of constraint programming, and their fitness is determined by the quality of solutions obtained for training instances.
CamPro: Camera-based Anti-Facial Recognition
The proliferation of images captured from millions of cameras and the advancement of facial recognition (FR) technology have made the abuse of FR a severe privacy threat.
iComMa: Inverting 3D Gaussian Splatting for Camera Pose Estimation via Comparing and Matching
We present a method named iComMa to address the 6D camera pose estimation problem in computer vision.
Personalized Federated Learning via ADMM with Moreau Envelope
Our experiments validate that FLAME, when trained on heterogeneous data, outperforms state-of-the-art methods in terms of model performance.
Towards High-quality HDR Deghosting with Conditional Diffusion Models
To address this challenge, we formulate the HDR deghosting problem as an image generation that leverages LDR features as the diffusion model's condition, consisting of the feature condition generator and the noise predictor.
Cross-modal Active Complementary Learning with Self-refining Correspondence
Recently, image-text matching has attracted more and more attention from academia and industry, which is fundamental to understanding the latent correspondence across visual and textual modalities.
Rethinking Superpixel Segmentation from Biologically Inspired Mechanisms
Recently, advancements in deep learning-based superpixel segmentation methods have brought about improvements in both the efficiency and the performance of segmentation.
AI-Copilot for Business Optimisation: A Framework and A Case Study in Production Scheduling
However, developing an LLM for problem formulation is challenging, due to training data, token limitations, and lack of appropriate performance metrics.
GeXSe (Generative Explanatory Sensor System): An Interpretable Deep Generative Model for Human Activity Recognition in Smart Spaces
The standard approach is based on a CNN model, which our MLP model outperforms. GeXSe offers two types of explanations: sensor-based activation maps and visual domain explanations using short videos.
AutoML in The Wild: Obstacles, Workarounds, and Expectations
Automated machine learning (AutoML) is envisioned to make ML techniques accessible to ordinary users.
An end-to-end multi-scale network for action prediction in videos
Unlike most existing methods with offline feature generation, our method directly takes frames as input and further models motion evolution on two different temporal scales. Therefore, we solve the complexity problems of the two stages of modeling and the problem of insufficient temporal and spatial information of a single scale.
MiLMo:Minority Multilingual Pre-trained Language Model
To solve the problem of scarcity of datasets on minority languages and verify the effectiveness of the MiLMo model, this paper constructs a minority multilingual text classification dataset named MiTC, and trains a word2vec model for each language.
Multi-fidelity Gaussian Process for Biomanufacturing Process Modeling with Small Data
In biomanufacturing, developing an accurate model to simulate the complex dynamics of bioprocesses is an important yet challenging task.
Enhancing Constraint Programming via Supervised Learning for Job Shop Scheduling
Finally, we demonstrate that hybridising the machine learning-based variable ordering methods with traditional domain-based methods is beneficial.
Adaptive Population-based Simulated Annealing for Uncertain Resource Constrained Job Scheduling
While a number of optimisation methods have been proposed to tackle the deterministic problem, the uncertainty associated with resource availability, an inevitable challenge in mining operations, has received less attention.
Learning Generalizable Models for Vehicle Routing Problems via Knowledge Distillation
Recent neural methods for vehicle routing problems always train and test the deep models on the same instance distribution (i. e., uniform).
Prerequisite-driven Q-matrix Refinement for Learner Knowledge Assessment: A Case Study in Online Learning Context
To overcome these issues, in this paper we propose a prerequisite-driven Q-matrix refinement framework for learner knowledge assessment (PQRLKA) in online context.
TiBERT: Tibetan Pre-trained Language Model
Then, we train the Tibetan monolingual pre-trained language model named TiBERT on the data and vocabulary.
Probabilistic spatial clustering based on the Self Discipline Learning (SDL) model of autonomous learning
Unsupervised clustering algorithm can effectively reduce the dimension of high-dimensional unlabeled data, thus reducing the time and space complexity of data processing.
Enhancing Column Generation by a Machine-Learning-Based Pricing Heuristic for Graph Coloring
In each iteration of CG, our MLPH leverages an ML model to predict the optimal solution of the pricing problem, which is then used to guide a sampling method to efficiently generate multiple high-quality columns.
Learning Primal Heuristics for Mixed Integer Programs
This paper proposes a novel primal heuristic for Mixed Integer Programs, by employing machine learning techniques.
Instance Space Analysis for the Car Sequencing Problem
We investigate an important research question for solving the car sequencing problem, that is, which characteristics make an instance hard to solve?
Bit thread, entanglement distillation, and entanglement of purification
We investigate the relations between bit thread, entanglement distillation and entanglement of purification in the holographic framework.
High Energy Physics - Theory
Hawking radiation from nonrotating singularity-free black holes in conformal gravity
Besides, we investigate the dependence of the greybody factor and the sparsity of Hawking radiation on the conformal parameters.
General Relativity and Quantum Cosmology
On the Efficiency of K-Means Clustering: Evaluation, Optimization, and Algorithm Selection
This paper presents a thorough evaluation of the existing methods that accelerate Lloyd's algorithm for fast k-means clustering.
Boosting Ant Colony Optimization via Solution Prediction and Machine Learning
In the first phase of our ML-ACO algorithm, an ML model is trained using a set of small problem instances where the optimal solution is known.
Generalization of Machine Learning for Problem Reduction: A Case Study on Travelling Salesman Problems
In this paper, we examine the generalization capability of a machine learning model for problem reduction on the classic travelling salesman problems (TSP).
Improving MMD-GAN Training with Repulsive Loss Function
To address this issue, we propose a repulsive loss function to actively learn the difference among the real data by simply rearranging the terms in MMD.
Ranked #19 on
Image Generation
on STL-10
Automatic Background Filtering Method for Roadside LiDAR Data
Background filtering is the preprocessing step to obtain the HRMTD of different roadway users from roadside LiDAR data.
Method of Tibetan Person Knowledge Extraction
Person knowledge extraction is the foundation of the Tibetan knowledge graph construction, which provides support for Tibetan question answering system, information retrieval, information extraction and other researches, and promotes national unity and social stability.
