检索结果-内蒙古大学图书馆

18th European-Alliance-for-Innovation (EAI) International Conference on Collaborative Computing - Networking, Applications and Worksharing (CollaborateCom)

作者： Cao, Ziwen Wang, Siye Sun, Degang Zhang, Yanfang Feng, Yue Jiang, Shang Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing Peoples R China

ISBN: (纸本)9783031243851;9783031243868

With the increasing popularity of Radio Frequency Identification (RFID) technology, indoor applications based on RFID trajectory data analysis are becoming more and more extensive, such as personnel location, tracking, and heat map analysis. The effectiveness of indoor applications relies greatly on high-quality trajectory data. However, due to the constraints of the device and environment, RFID readers will miss reading data in real-world practice, which leads to a large number of indoor trajectories that are incomplete. To enhance trajectory data and support indoor applications more efficiently, many trajectory recovery methods to infer trajectories in free space have been proposed. However, existing methods cannot achieve automated inference and have low accuracy in inferring indoor trajectories. In this paper, we propose an Indoor Trajectory Automatic Recovery framework, ITAR, to recover missing points in indoor trajectories. ITAR adopts a sequence-to-sequence learning architecture to generate complete trajectories. We first construct a directed graph for each trajectory and use a graph neural network to capture complex location transition patterns. Then, we propose a multi-head attention mechanism to capture long-term correlations among trajectory points to improve performance. We conduct extensive experiments on synthetic and real datasets, and the results show that ITAR is superior in performance and robustness.

关键词： Trajectory recovery sequence-to-sequence model Radio frequency identification Graph neural network

来源：评论

学校读者我要写书评

暂无评论

A confidence-based knowledge integration framework for cross-domain table question answering

引用

KNOWLEDGE-BASED SYSTEMS 2024年 306卷

作者： Fan, Yuankai Ren, Tonghui Huang, Can Zheng, Beini Jing, Yinan He, Zhenying Li, Jinbao Li, Jianxin Fudan Univ Sch Comp Sci Shanghai Peoples R China Edith Cowan Univ Sch Business & Law Joondalup Australia Qilu Univ Technol Shandong Artificial Intelligence Inst Shandong Acad Sci Sch Math & Stat Jinan Peoples R China

Recent advancements in TableQA leverage sequence-to-sequence (Seq2seq) deep learning models to accurately respond to natural language queries. These models achieve this by converting the queries into SQL queries, using information drawn from one or more tables. However, Seq2seq models often produce uncertain (low- confidence) predictions when distributing probability mass across multiple outputs during a decoding step, frequently yielding translation errors. To tackle this problem, we present CKIF, a confidence-based knowledge integration framework that uses a two-stage deep-learning-based ranking technique to mitigate the low- confidence problem commonly associated with Seq2seq models for TableQA. The core idea of CKIF is to introduce a flexible framework that seamlessly integrates with any existing Seq2seq translation models to enhance their performance. Specifically, by inspecting the probability values in each decoding step, CKIF first masks out each low-confidence prediction from the predicted outcome of an underlying Seq2seq model. Subsequently, CKIF integrates prior knowledge of query language to generalize masked-out queries, enabling the generation of all possible queries and their corresponding NL expressions. Finally, a two-stage deep- learning ranking approach is developed to evaluate the semantic similarity of NL expressions to a given NL question, hence determining the best-matching result. Extensive experiments are conducted to investigate CKIF by applying it to five state-of-the-art Seq2seq models using a widely used public benchmark. The experimental results indicate that CKIF consistently enhances the performance of all the Seq2seq models, demonstrating its effectiveness for better supporting TableQA.

关键词： Table question answering Natural language interfaces sequence-to-sequence model Confidence estimation Similarity ranking

来源：评论

学校读者我要写书评

暂无评论

A Hybrid CNN-Transformer Architecture for Semantic Segmentation of Radar Sounder data

A Hybrid CNN-Transformer Architecture for Semantic Segmentat...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Ghosh, Raktim Bovolo, Francesca Univ Trento FBK Trento Italy FBK Trento Italy

ISBN: (数字)9781665427920

ISBN: (纸本)9781665427920

Radar Sounders (RSs) are space-borne and airborne sensors operating on the nadir-looking geometry to collect subsurface information by transmitting linearly modulated electromagnetic (EM) pulses and receiving backscattered (reflected from different subsurface targets) echoes. The echoes are coherently represented to generate radargrams. A radargram is used to characterize subsurface target structures. Interestingly, radargram signals depict sequential structures due to linearly homogeneous subsurface target features such as ice layers. Several automatic techniques are proposed to characterize the subsurface targets in the radargrams mostly associated with the probabilistic models or CNN-based deep learning models. The CNN-based architectures explicitly model the local spatial high dimensional contexts which are often infeasible for establishing the long-range sequential contextual relationship between local spatial features. Motivated by the aforementioned fact, we propose a hybrid CNN-Transformer-based encoder-decoder architectural framework for addressing the long-range sequential contextual dependencies within the sequential structures of RS signals. We tested the architecture on Multi-channel Coherent Radar Depth Sounder (MCoRDS) dataset. Experimental results confirm the capability of Transformers to characterize the subsurface targets.

关键词： Semantic Segmentation Transformers sequence-to-sequence model Radar Sounder

来源：评论

学校读者我要写书评

暂无评论

An FFT-based CNN-Transformer Encoder for Semantic Segmentation of Radar Sounder Signal 28

An FFT-based CNN-Transformer Encoder for Semantic Segmentati...

引用

Conference on Image and Signal Processing for Remote Sensing XXVIII

作者： Ghosh, Raktim Bovolo, Francesca Univ Trento Trento Italy Fdn Bruno Kessler Trento Italy

ISBN: (纸本)9781510655386;9781510655379

Radar Sounders (RSs) are sensors operating in the nadir-looking geometry (with HF or VHF bands) by transmitting modulated electromagnetic (EM) pulses and receiving the backscattering response from different subsurface targets. Recently, convolutional neural network (CNN) architectures were established for characterizing RS signals under the semantic segmentation framework. In this paper, we design a Fast Fourier Transform (FFT) based CNN-Transformer encoder to effectively capture the long-range contexts in the radargram. In our hybrid architecture, CNN models the high-dimensional local spatial contexts, and the Transformer establishes the global spatial contexts between the local spatial ones. To overcome Transformer complex self-attention layers by reducing learnable parameters;- we replace the self-attention mechanism of the Transformer with unparameterized FFT modules as depicted in FNet architecture for Natural Language Processing (NLP). The experimental results on the MCoRDS dataset indicate the capability of the CNN-Transformer encoder along with the unparameterized FFT modules to characterize the radargram with limited accuracy cost and by reducing the time consumption. A comparative analysis is carried out with the state-of-the-art Transformer-based architecture.

关键词： radar sounder (RS) semantic segmentation transformers sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

Improving Open Information Extraction with Distant Supervision Learning

引用

NEURAL PROCESSING LETTERS 2021年第5期53卷 3287-3306页

作者： Han, Jiabao Wang, Hongzhi Harbin Inst Technol Sch Comp Sci & Technol Harbin 150001 Peoples R China

Open information extraction (Open IE), as one of the essential applications in the area of Natural Language Processing (NLP), has gained great attention in recent years. As a critical technology for building Knowledge Bases (KBs), it converts unstructured natural language sentences into structured representations, usually expressed in the form of triples. Most conventional open information extraction approaches leverage a series of manual pre-defined extraction patterns or learn patterns from labeled training examples, which requires a large number of human resources. Additionally, many Natural Language Processing tools are involved, which leads to error accumulation and propagation. With the rapid development of neural networks, neural-based models can minimize the error propagation problem, but it also faces the problem of data-hungry in supervised learning. Especially, they leverage existing Open IE tools to generate training data, and it causes data quality issues. In this paper, we employ a distant supervision learning approach to improve the Open IE task. We conduct extensive experiments by employing two popular sequence-to-sequence models (RNN and Transformer) and a large benchmark data set to demonstrate the performance of our approach.

关键词： Distant supervision learning Open information extraction Neural network sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

Summary-aware attention for social media short text abstractive summarization

引用

NEUROCOMPUTING 2021年 425卷 290-299页

作者： Wang, Qianlong Ren, Jiangtao Sun Yat Sen Univ Sch Data & Comp Sci Guangdong Prov Key Lab Computat Sci Guangzhou Guangdong Peoples R China

Neural sequence-to-sequence (Seq2Seq) models are currently dominant approaches in social media short text abstractive summarization task. However, the computation of source attention weight in Seq2Seq models does not fully consider the information of the previously generated summary, which harms the coherence of the summary. In addition, given the noisy source text, it is difficult for Seq2Seq models to learn an accurate source context. To address these two shortcomings, we propose summary-aware attention for social media short text abstractive summarization. In this work, we use the source hidden states and attended summary vectors to compute summary-aware attention weight. The attended summary vectors contribute to generate a coherent summary. Moreover, under the guidance of the attended summary vectors, the attention mechanism increases the weight of the related content and reduces the weight of noise. Following the previous work, we evaluate our model on a popular Chinese social media dataset. Both automatic and human evaluation results demonstrate that our model achieves significant improvements compared with strong baselines.

关键词： Abstractive summarization Attention mechanism sequence-to-sequence model Social media short text

来源：评论

学校读者我要写书评

暂无评论

AttentionHTR: Handwritten Text Recognition Based on Attention Encoder-Decoder Networks 15th

AttentionHTR: Handwritten Text Recognition Based on Attentio...

引用

15th IAPR International Workshop on Document Analysis Systems (DAS)

作者： Kass, Dmitrijs Vats, Ekta Uppsala Univ Dept Informat Technol Uppsala Sweden Uppsala Univ Ctr Digital Humanities Uppsala Dept ALM Uppsala Sweden

ISBN: (纸本)9783031065552;9783031065545

This work proposes an attention-based sequence-to-sequence model for handwritten word recognition and explores transfer learning for data-efficient training of HTR systems. To overcome training data scarcity, this work leverages models pre-trained on scene text images as a starting point towards tailoring the handwriting recognition models. ResNet feature extraction and bidirectional LSTM-based sequence modeling stages together form an encoder. The prediction stage consists of a decoder and a content-based attention mechanism. The effectiveness of the proposed end-to-end HTR system has been empirically evaluated on a novel multi-writer dataset Imgur5K and the IAM dataset. The experimental results evaluate the performance of the HTR framework, further supported by an in-depth analysis of the error cases. Source code and pre-trained models are available at GitHub (https://***/dmitrijsk/AttentionHTR).

关键词： Handwritten text recognition Attention encoder-decoder networks sequence-to-sequence model Transfer learning Multi-writer

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion Recognition Considering Nonverbal Vocalization in Affective Conversations

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2021年 29卷 1675-1686页

作者： Hsu, Jia-Hao Su, Ming-Hsiang Wu, Chung-Hsien Chen, Yi-Hsuan Natl Cheng Kung Univ Dept Comp Sci & Informat Engn Tainan 70101 Taiwan

In real-life communication, nonverbal vocalization such as laughter, cries or other emotion interjections, within an utterance play an important role for emotion expression. In previous studies, only few emotion recognition systems consider nonverbal vocalization, which naturally exists in our daily conversation. In this work, both verbal and nonverbal sounds within an utterance are considered for emotion recognition of real-life affective conversations. Firstly, a support vector machine (SVM)-based verbal and nonverbal sound detector is developed. A prosodic phrase auto-tagger is further employed to extract the verbal/nonverbal sound segments. For each segment, the emotion and sound feature embeddings are respectively extracted using the deep residual networks (ResNets). Finally, a sequence of the extracted feature embeddings for the entire dialog turn are fed to an attentive long short-term memory (LSTM)-based sequence-to-sequence model to output an emotional sequence as recognition result. The NNIME corpus (The NTHU-NTUA Chinese interactive multimodal emotion corpus), which consists of verbal and nonverbal sounds, was adopted for system training and testing. 4766 single speaker dialogue turns in the audio data of the NNIME corpus were selected for evaluation. The experimental results showed that nonverbal vocalization was helpful for speech emotion recognition. For comparison, the proposed method based on decision-level fusion achieved an accuracy of 61.92% for speech emotion recognition outperforming the traditional methods as well as the feature-level and model-level fusion approaches.

关键词： Speech recognition Emotion recognition Feature extraction Artificial neural networks Databases Speech processing Training Speech emotion recognition prosodic phrase nonverbal vocalization convolutional neural network long-short term memory sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

Automated Generation of Chinese Lyrics Based on Melody Emotions

引用

IEEE ACCESS 2021年 9卷 98060-98071页

作者： Huang, Yin-Fu You, Kai-Cheng Natl Yunlin Univ Sci & Technol Dept Comp Sci & Informat Engn Touliu 64002 Yunlin Taiwan

Natural Language Processing enables computers to understand human natural languages and assists humans to perform many tasks. Recently, language research was gradually moving towards the field of natural language generation, and lyrics generation is one of these research directions. In the past, many studies have explored how to generate lyrics using seeds or prompt words. But, they usually ignored the relationship between music and lyrics and even melody emotions when generating lyrics. In this paper, we propose the Chinese lyrics generation system based on notes and melody emotions. In the first phase, a support vector regression model is trained to detect melody emotions. In the second phase, a sequence-to-sequence model is trained to generate lyrics using notes, melody emotions, and lyrics. Finally, we conduct the experiments and evaluate the detected melody emotions and the generated lyrics. Results show that the generated lyrics have fluent sentences, and the sentences are with connected semantics.

关键词： Feature extraction Training Rhythm Natural language processing Timbre Semantics Harmonic analysis Lyric generation melody emotion detection natural language processing sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

Emotional dialog generation via multiple classifiers based on a generative adversarial network

引用

Virtual Reality & Intelligent Hardware 2021年第1期3卷 18-32页

作者： Wei CHEN Xinmiao CHEN Xiao SUN School of Computer and Information Hefei University of TechnologyHefei 230601China

Background Human-machine dialog generation is an essential topic of research in the field of natural language *** high-quality,diverse,fluent,and emotional conversation is a challenging *** on continuing advancements in artificial intelligence and deep learning,new methods have come to the forefront in recent *** particular,the end-to-end neural network model provides an extensible conversation generation framework that has the potential to enable machines to understand semantics and automatically generate ***,neural network models come with their own set of questions and *** basic conversational model framework tends to produce universal,meaningless,and relatively"safe"*** Based on generative adversarial networks(GANs),a new emotional dialog generation framework called EMC-GAN is proposed in this study to address the task of emotional dialog *** proposed model comprises a generative and three discriminative *** generator is based on the basic sequence-to-sequence(Seq2Seq)dialog generation model,and the aggregate discriminative model for the overall framework consists of a basic discriminative model,an emotion discriminative model,and a fluency discriminative *** basic discriminative model distinguishes generated fake sentences from real sentences in the training *** emotion discriminative model evaluates whether the emotion conveyed via the generated dialog agrees with a pre-specified emotion,and directs the generative model to generate dialogs that correspond to the category of the pre-specified ***,the fluency discriminative model assigns a score to the fluency of the generated dialog and guides the generator to produce more fluent *** Based on the experimental results,this study confirms the superiority of the proposed model over similar existing models with respect to emotional accuracy,fluency,and *** The proposed EMC-

关键词： Emotional dialog generation sequence-to-sequence model Emotion classification Generative adversarial networks Multiple classifiers

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：