检索结果-内蒙古大学图书馆

BDCore: bidirectional decoding with Co-graph Representation for Joint Entity and Relation Extraction

KNOWLEDGE-BASED SYSTEMS 2024年 294卷

作者： Zeng, Daojian Zhao, Chao Li, Dongye Dai, Jianhua Hunan Normal Univ Hunan Prov Key Lab Intelligent Comp & Language Inf Changsha Peoples R China Changsha Univ Sci & Technol Sch Comp & Commun Engn Changsha Peoples R China

Relation extraction has become a crucial step for the automatic construction of Knowledge Graph (KG). Recently, researchers leverage Sequence-to-Sequence (Seq2Seq) models for Joint Entity and Relation Extraction (JERE). Nevertheless, traditional decoding methods entail the generation of the target sequence incrementally from left to right by the decoder, without the ability to revise earlier predictions when errors occur. This limitation becomes evident when decoding errors manifest prior to the current decoding step. Furthermore, the interrelations among triplets originating from the same sentence exhibit a robust correlation, which has been overlooked. In this paper, we propose B idirectional D ecoding with Co -graph re presentation (BDCore) to address the issues mentioned above. Specifically, we first introduce a backward decoder to decode the target sequence in a reverse order. Then, the forward decoder introduces two attention mechanisms to simultaneously considering the hidden states of the encoder and the backward decoder. Thus, the backward decoding information helps to alleviate the negative impact of the forward decoding errors. Besides, we construct a relation co-occurrence graph (Co-graph) and exploit Graph Convolutional Network (GCN) to capture the relation correlation. The extensive experiments demonstrate the benefits of the proposed bidirectional decoding and co-graph representation for relation extraction. Compared to the previous methods, our approach significantly outperforms the baselines on the NYT benchmark.

关键词： Joint relation extraction bidirectional decoding Seq2Seq Graph Convolutional Network Backward decoder

来源：评论

学校读者我要写书评

暂无评论

Exploiting reverse target-side contexts for neural machine translation via asynchronous bidirectional decoding

引用

ARTIFICIAL INTELLIGENCE 2019年 277卷 103168-000页

作者： Su, Jinsong Zhang, Xiangwen Lin, Qian Qin, Yue Yao, Junfeng Liu, Yang Xiamen Univ Xiamen 361005 Fujian Peoples R China Tsinghua Univ Beijing 100084 Peoples R China

Based on a unified encoder-decoder framework with attentional mechanism, neural machine translation (NMT) models have attracted much attention and become the mainstream in the community of machine translation. Generally, the NMT decoders produce translation in a left-to-right way. As a result, only left-to-right target-side contexts from the generated translations are exploited, while the right-to-left target-side contexts are completely unexploited for translation. In this paper, we extend the conventional attentional encoder-decoder NMT framework by introducing a backward decoder, in order to explore asynchronous bidirectional decoding for NMT. In the first step after encoding, our backward decoder learns to generate the target-side hidden states in a right-to-left manner. Next, in each timestep of translation prediction, our forward decoder concurrently considers both the source-side and the reverse target-side hidden states via two attention models. Compared with previous models, the innovation in this architecture enables our model to fully exploit contexts from both source side and target side, which improve translation quality altogether. We conducted experiments on NIST Chinese-English, WMT English-German and Finnish-English translation tasks to investigate the effectiveness of our model. Experimental results show that (1) our improved RNN-based NMT model achieves significant improvements over the conventional RNNSearch by 1.44/-3.02, 1.11/-1.01, and 1.23/-1.27 average BLEU and TER points, respectively;and (2) our enhanced Transformer outperforms the standard Transformer by 1.56/-1.49, 1.76/-2.49, and 1.29/-1.33 average BLEU and TER points, respectively. (C). 2019 Elsevier B.V. All rights reserved.

关键词： Neural machine translation bidirectional decoding Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Adaptive graph transformer with future interaction modeling for multi-agent trajectory prediction

引用

KNOWLEDGE-BASED SYSTEMS 2025年 316卷

作者： Chen, Xiaobo Wang, Junyu Deng, Fuwen Li, Zuoyong Shandong Technol & Business Univ Sch Comp Sci & Technol Yantai 264005 Peoples R China Minjiang Univ Sch Comp & Big Data Fuzhou 350121 Peoples R China

Forecasting the trajectories of traffic agents is essential for autonomous systems such as self-driving cars and social robots to guarantee safety in crowded scenarios. Capturing social interactions between agents and generating informative future features bring great challenges to accurate trajectory prediction. To this end, this paper proposes a novel multi-agent trajectory prediction model called AGTFI based on the adaptive graph transformer and future interaction modeling. First, an adaptive graph transformer (AGT) proficient at extracting node and edge features is introduced to capture the complex social interactions between traffic agents. Moreover, a two-stage prediction approach is devised where the first stage is devoted to generating pre-estimated future motion features by bidirectional corrected GRU (BCGRU) and the second stage further incorporates future social interactions into BCGRU to reduce prediction errors. Quantitative and qualitative evaluations of AGTFI on benchmark datasets, including ETH-UCY, SDD, and INTERACTION demonstrate the effectiveness of our model. Ablation studies are conducted to verify the rationale behind the model components.

关键词： Trajectory prediction Graph transformer Attention mechanism bidirectional decoding

来源：评论

学校读者我要写书评

暂无评论

Convolutional Codes with Optimum bidirectional Distance Profile

引用

PROBLEMS OF INFORMATION TRANSMISSION 2023年第3期59卷 181-203页

作者： Stanojevic, I. Senk, V. Univ Novi Sad Fac Tech Sci Novi Sad Serbia

We define the bidirectional distance profile (BDP) of a convolutional code as the minimum of the distance profiles of the code and its corresponding "reverse" code. We present tables of codes with the optimum BDP (OBDP), which minimize the average complexity of bidirectional sequential decoding algorithms. The computer search is accelerated by the facts that optimum distance profile (ODP) codes of larger memory must have ODP codes of smaller memory as their "prefixes", and that OBDP codes can be obtained by "concatenating" ODP and reverse ODP codes of smaller memory. We compare the performance of OBDP codes and other codes by simulation.

关键词： convolutional codes distance profile bidirectional decoding

来源：评论

学校读者我要写书评

暂无评论

Effective Named Entity Recognition with Boundary-aware bidirectional Neural Networks 21

Effective Named Entity Recognition with Boundary-aware Bidir...

引用

30th World Wide Web Conference (WWW)

作者： Li, Fei Wang, Zheng Hui, Siu Cheung Liao, Lejian Song, Dandan Xu, Jing Beijing Inst Technol Sch Comp Sci & Technol Beijing Peoples R China Beijing Engn Res Ctr High Volume Language Informa Beijing Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn Singapore Singapore

ISBN: (纸本)9781450383127

Named Entity Recognition (NER) is a fundamental problem in Natural Language Processing and has received much research attention. Although the current neural-based NER approaches have achieved the state-of-the-art performance, they still suffer from one or more of the following three problems in their architectures: (1) boundary tag sparsity, (2) lacking of global decoding information;and (3) boundary error propagation. In this paper, we propose a novel Boundary-aware bidirectional Neural Networks (Ba-BNN) model to tackle these problems for neural-based NER. The proposed Ba-BNN model is constructed based on the structure of pointer networks for tackling the first problem on boundary tag sparsity. Moreover, we also use a boundary-aware binary classifier to capture the global decoding information as input to the decoders. In the Ba-BNN model, we propose to use two decoders to process the information in two different directions (i.e., from left-to-right and right-to-left). The final hidden states of the left-to-right decoder are obtained by incorporating the hidden states of the right-to-left decoder in the decoding process. In addition, a boundary retraining strategy is also proposed to help reduce boundary error propagation caused by the pointer networks in boundary detection and entity classification. We have conducted extensive experiments based on three NER benchmark datasets. The performance results have shown that the proposed Ba-BNN model has outperformed the current state-of-the-art models.

关键词： Named entity recognition boundary retraining bidirectional decoding pointer networks

来源：评论

学校读者我要写书评

暂无评论

BiTransformer: augmenting semantic context in video captioning via bidirectional decoder

引用

MACHINE VISION AND APPLICATIONS 2022年第5期33卷 77-77页

作者： Zhong, Maosheng Zhang, Hao Wang, Yong Xiong, Hao Jiangxi Normal Univ 99 Ziyang Ave Nanchang Jiangxi Peoples R China

Video captioning is an important problem involved in many applications. It aims to generate some descriptions of the content of a video. Most of existing methods for video captioning are based on the deep encoder-decoder models, particularly, the attention-based models (say Transformer). However, the existing transformer-based models may not fully exploit the semantic context, that is, only using the left-to-right style of context but ignoring the right-to-left counterpart. In this paper, we introduce a bidirectional (forward-backward) decoder to exploit both the left-to-right and right-to-left styles of context for the Transformer-based video captioning model. Thus, our model is called bidirectional Transformer (dubbed BiTransformer). Specifically, in the bridge of the encoder and forward decoder (aiming to capture the left-to-right context) used in the existing Transformer-based models, we plug in a backward decoder to capture the right-to-left context. Equipped with such bidirectional decoder, the semantic context of videos will be more fully exploited, resulting in better video captions. The effectiveness of our model is demonstrated over two benchmark datasets, i.e., MSVD and MSR-VTT,via comparing to the state-of-the-art methods. Particularly, in terms of the important evaluation metric CIDEr, the proposed model outperforms the state-of-the-art models with improvements of 1.2% in both datasets.

关键词： Video captioning bidirectional decoding Transformer

来源：评论

学校读者我要写书评

暂无评论

A Novel Algorithm of Tail Biting Convolutional Code Decoder for Low Cost Hardware Implementation

A Novel Algorithm of Tail Biting Convolutional Code Decoder ...

引用

International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)

作者： Ramdani, Ahmad Zaky Adiono, Trio Inst Teknol Bandung Ctr Microelect Bandung Indonesia

ISBN: (纸本)9781467364997

Tail-biting convolutional codes (TBCC) have been applied in many recent modern communication standards such as LTE and WIMAX. TBCC is a method applied in conventional convolutional code by replacing a fixed zero-tail with tail-biting data constrains to achieve a better coding efficiency. This modification makes the decoding process becomes much more complex. Due to impracticality of the optimum decoding algorithm such as brute force, recently some suboptimum algorithms have been developed but it still leaves a large amount of computation due to the iterative nature wherein the number of iterations depends on the received codeword causes inefficient system for implementation, especially for real time applications. In this paper we offer a new algorithm that is specific to low cost hardware implementation. Low cost criteria are addressed to minimum amount of computation for each decoding process. In addition to causing smaller area consumption, the lack of computing process will also make decoding processing time becomes faster. This algorithm that we call reverse trellis algorithm also offers a fixed amount of computation regardless to the received codeword, thus will not require extra memory consumption as it being on an implementation. Taking a case study on TBCC configuration for LTE, proposed algorithm requires 5712 adding operations and 3008 inverting operations. A significant decrease compared to 286736, adding 143360 inverting for Brute Force and 45079976738816 adding 1099511627776 inverting for all possible fixed tail ML decoder. In the performance of BER, reverse trellis algorithm is able to deliver improved by more than 1 dB compared to direct terminating ML decoder.

关键词： ML decoder tail-biting convolutional code bidirectional decoding low cost implementation

来源：评论

学校读者我要写书评

暂无评论

Weakly Symmetric Fix-Free Codes

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2014年第9期60卷 5500-5515页

作者： Aghajan, Adel Khosravifard, Mohammadali Isfahan Univ Technol Dept Elect & Comp Engn Esfahan *** Iran

bidirectional decoding improves the error resilience of the fix-free codes, which is important in some applications like video coding. However, in general, two separate decoders must be designed for forward and backward decoding and hence, the cost of decoding is almost doubled. For the symmetric fix-free codes, although the forward and backward decoders are the same, the redundancy could be much greater than the case of asymmetric fix-free codes. In this paper, a class of fix-free codes, called weakly symmetric, is studied. A code is weakly symmetric if the reverse of each codeword itself is a codeword. This imposes a much weaker constraint on the codewords than what is necessitated by the symmetric codes, i.e., each codeword must be equal to its reverse. We show that the forward and backward decoders of a weakly symmetric fix-free code are essentially the same. In addition, it is shown that two significant sufficient conditions for the existence of asymmetric fix-free codes are also applicable to the case of weakly symmetric fix-free codes. As a result, we conclude that for any memoryless source, the redundancy of the optimal weakly symmetric fix-free code is at most 1.0817 bits. Moreover, it can be only 0.8 bit greater than the redundancy of the Huffman code in the worst case. In summary, weakly symmetric fix-free codes can be regarded as an option by which one can to some extent achieve the low redundancy of asymmetric fix-free codes and the low-cost bidirectional decoding of symmetric fix-free codes, simultaneously.

关键词： Symmetric fix-free codes asymmetric fix-free codes bidirectional decoding redundancy Kraft sum

来源：评论

学校读者我要写书评

暂无评论

Error-Resilient H.264/AVC Video Transmission Using Two-Way Decodable Variable Length Data Block

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2010年第3期20卷 340-350页

作者： Gao, Shaoshuai Ma, Kai-Kuang Chinese Acad Sci Grad Univ Sch Informat Sci & Engn Beijing 100049 Peoples R China Nanyang Technol Univ Sch Elect & Elect Engn Singapore 639798 Singapore

Standard video coders utilize variable length coding (VLC) to obtain more data compression in addition to what lossy coding has achieved at the expense of making the compressed bitstream very vulnerable to channel errors. Even a 1-bit error incurred in the bitstream may cause the follow-up bitstream to be either erroneously decoded or completely undecodable, and this could further result in error propagation. To mitigate this phenomenon, a new VLC coding scheme is proposed in this paper, called the two-way decodable variable length data block (TDVLDB), which allows the compressed bitstream to be bidirectionally decodable without exploiting data partitioning. The proposed TDVLDB scheme is able to effectively recover more uncorrupted data from the corrupted packets. Furthermore, it is able to correct some, if not all, channel errors of a finite-length burst error. To effectively identify the location of the first actual error incurred within the current slice, a bitstream similarity measurement (BSM) algorithm is proposed. Note that the proposed TDVLDB scheme is generic in the sense that it can be exploited in any image or video coding framework as long as it involves the use of VLC and requires error-resilience capability. In this paper, the proposed TDVLDB is incorporated into the H.264/advanced video coding (AVC) coder to evaluate its error-resilience performance in terms of rate-distortion coding efficiency. Compared with the baseline H.264/AVC coding, the TDVLDB-incorporated H.264/AVC-based coding scheme has demonstrated significant objective and subjective video quality improvements when the bitstream is transmitted over error-prone channels.

关键词： bidirectional decoding error concealment error-resilient video coding H.264/AVC resynchronization reversible variable length coding two-way decoding wireless video transmission

来源：评论

学校读者我要写书评

暂无评论

bidirectional Fano Algorithm for High Throughput Sequential decoding

Bidirectional Fano Algorithm for High Throughput Sequential ...

引用

20th IEEE Symposium on Personal, Indoor and Mobile Radio Communications

作者： Xu, Ran Kocak, Taskin Woodward, Graeme Morris, Kevin Dolwin, Craig Univ Bristol Ctr Commun Res Merchant Venturers Bldg Bristol Avon England Toshiba Res Europe Ltd Telecomm Res Lab Queens Square Bristol Avon England

ISBN: (纸本)9781424451234

Various techniques, such as bidirectional search, have been employed in sequential decoding to reduce the decoding delay. In this paper, a bidirectional Fano algorithm (BFA) is proposed, in which a forward decoder (FD) and a backward decoder (BD) search in the opposite direction simultaneously. It is shown that the proposed BFA can reduce the average decoding delay by at least 50% compared to the unidirectional Fano algorithm (UFA). Due to the reduction in the variability of the computational effort by using bidirectional search, there is even higher decoding throughput improvement at low signal-to-noise-ratio (SNR). For example at Eb/No=3dB, there is 300% throughput improvement by using the BFA decoding compared to the conventional UFA decoding. The proposed BFA decoding technique can be employed in very high throughput wireless communication systems with low hardware complexity and power consumption.

关键词： bidirectional decoding Fano algorithm high throughput decoding sequential decoding

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：