检索结果-内蒙古大学图书馆

31st ACM International Conference on Information and Knowledge Management (CIKM)

作者： Feng, Jinjia Wang, Zhen Li, Yaliang Ding, Bolin Wei, Zhewei Xu, Hongteng Peng Cheng Lab Shenzhen Peoples R China Renmin Univ China Beijing Peoples R China Alibaba Grp Hangzhou Peoples R China Alibaba Grp Bellevue WA USA

ISBN: (纸本)9781450392365

Masked autoencoder (MAE), as an effective self-supervised learner for computer vision and natural language processing, has been recently applied to molecule representation learning. In this paper, we identify two issues in applying MAE to pre-train Transformer-based models on molecular graphs that existing works have ignored. (1) As only atoms are abstracted as tokens and then reconstructed, the chemical bonds are not decided in the decoded molecule, making molecules with different arrangements of the same atoms indistinguishable. (2) Although a high mask ratio that corresponds to a challenging reconstruction task has been proved beneficial in the vision domain, it cannot be trivially leveraged on molecular graphs as there is less redundancy of information in graph data. To resolve these issues, we propose a novel framework, Molecular graph Mask AutoEncoder (MGMAE). As the first step in MGMAE, we transform each molecular graph into a heterogeneous atom-bond graph to fully use the bond attributes and design unidirectional position encoding for such graphs. Then we propose a hybrid masking mechanism that exploits the complementary nature between atoms' attributive and spatial features. Meanwhile, we compensate for the mask embedding by a dynamic aggregation representation that exploits the correlations between topologically adjacent tokens. As a result, MGMAE can reconstruct the masked atoms, the masked bonds, and the relative distance among atoms simultaneously, with a high mask ratio. We compare MGMAE with the state-of-the-art methods on various molecular benchmarks and show the competitiveness of MGMAE in both regression and classification tasks.

关键词： Transformer graph Representation Learning Molecular Property Prediction Self-supervised Learning

来源：评论

学校读者我要写书评

暂无评论

IRRGN: An Implicit Relational Reasoning graph Network for Multi-turn Response Selection

IRRGN: An Implicit Relational Reasoning Graph Network for Mu...

引用

2022 Conference on Empirical methods in natural language processing, EMNLP 2022

作者： Deng, Jingcheng Dai, Hengwei Guo, Xuewei Ju, Yuanchen Peng, Wei College of Computer and Information Science Southwest University China yz-intelligence Inc Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China

The task of response selection in multi-turn dialogue is to find the best option from all candidates. In order to improve the reasoning ability of the model, previous studies pay more attention to using explicit algorithms to model the dependencies between utterances, which are deterministic, limited and inflexible. In addition, few studies consider differences between the options before and after reasoning. In this paper, we propose an Implicit Relational Reasoning graph Network to address these issues, which consists of the Utterance Relational Reasoner (URR) and the Option Dual Comparator (ODC). URR aims to implicitly extract dependencies between utterances, as well as utterances and options, and make reasoning with relational graph convolutional networks. ODC focuses on perceiving the difference between the options through dual comparison, which can eliminate the interference of the noise options. Experimental results on two multi-turn dialogue reasoning benchmark datasets MuTual and MuTualplus show that our method significantly improves the baseline of four pre-trained language models and achieves state-of-the-art performance. The model surpasses human performance for the first time on the MuTual dataset. Our code is released in the link. © 2022 Association for Computational Linguistics.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Wikigraphs: A Wikipedia Text - Knowledge graph Paired Dataset 15

WikiGraphs: A Wikipedia Text - Knowledge Graph Paired Datase...

引用

15th workshop on graph-based methods for natural language processing, Textgraphs 2021

作者： Wang, Luyu Li, Yujia Aslan, Ozlem Vinyals, Oriol DeepMind London United Kingdom

ISBN: (纸本)9781954085381

We present a new dataset ofWikipedia articles each paired with a knowledge graph, to facilitate the research in conditional text generation, graph generation and graph representation learning. Existing graph-text paired datasets typically contain small graphs and short text (1 or few sentences), thus limiting the capabilities of the models that can be learned on the data. Our new datasetWikigraphs is collected by pairing each Wikipedia article from the established WikiText-103 benchmark (Merity et al., 2016) with a subgraph from the Freebase knowledge graph (Bollacker et al., 2008). This makes it easy to benchmark against other state-of-the-art text generative models that are capable of generating long paragraphs of coherent text. Both the graphs and the text data are of significantly larger scale compared to prior graph-text paired datasets. We present baseline graph neural network and transformer model results on our dataset for 3 tasks: graph → text generation, graph → text retrieval and text → graph retrieval. We show that better conditioning on the graph provides gains in generation and retrieval quality but there is still large room for improvement. © 2021 Association for Computational Linguistics.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

graphVCM: Virtual Center Mixing with Distance-Aware Regulation for Class Imbalanced Node Classification

GraphVCM: Virtual Center Mixing with Distance-Aware Regulati...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Ren, Yixiao Han, Yunfei Wang, Yi Luo, Zhengdong Liu, Jinlong Ma, Yupeng Xinjiang Technical Institute of Physics & Chemistry Chinese Academy of Sciences Urumqi China University of Chinese Academy of Sciences Beijing China Xinjiang Laboratory of Minority Speech and Language Information Processing Urumqi China

ISBN: (纸本)9798350368741

Class imbalance is a prevalent issue in real-world graph-structure data, such as social and citation networks, posing significant challenges for graph Neural Networks (GNNs). Existing solutions often focus on balancing class distributions via oversampling techniques, which may lead to overfitting and blurred decision boundaries between majority and minority classes. To address this issue, we propose graphVCM, a novel virtual center mixing with distance-aware regulation approach for class imbalanced node classification. graphVCM first leverages spectral clustering to generate virtual center nodes, representing the features of majority class samples. These virtual centers are then mixed with minority class nodes to synthesize new nodes for enhancing minority class representation. Moreover, we introduce a distance-aware regulation module to optimize the inter-class decision boundaries by simultaneously maximizing inter-class distances and minimizing intra-class distances. Extensive experiments on multiple public datasets demonstrate that graphVCM consistently outperforms state-of-the-art methods and effectively alleviates the negative impact of class imbalance. © 2025 IEEE.

关键词： class imbalance data augmentation node classification virtual centroid features

来源：评论

学校读者我要写书评

暂无评论

PAIGE: Personalized Adaptive Interactions graph Encoder for Query Rewriting in Dialogue Systems

PAIGE: Personalized Adaptive Interactions Graph Encoder for ...

引用

2022 Conference on Empirical methods in natural language processing, EMNLP 2022

作者： Bis, Daniel Gupta, Saurabh Hao, Jie Fan, Xing Guo, Chenlei Amazon Alexa AI LinkedIn

ISBN: (纸本)9781952148255

Unexpected responses or repeated clarification questions from conversational agents detract from the users’ experience with technology meant to streamline their daily tasks. To reduce these frictions, Query Rewriting (QR) techniques replace transcripts of faulty queries with alternatives that lead to responses that satisfy the users’ needs. Despite their successes, existing QR approaches are limited in their ability to fix queries that require considering users’ personal preferences. We improve QR by proposing Personalized Adaptive Interactions graph Encoder (PAIGE). PAIGE is the first QR architecture that jointly models user’s affinities and query semantics end-to-end. The core idea is to represent previous user-agent interactions and world knowledge in a structured form — a heterogeneous graph — and apply message passing to propagate latent representations of users’ affinities to refine utterance embeddings. Using these embeddings, PAIGE can potentially provide different rewrites given the same query for users with different preferences. Our model, trained without any human-annotated data, improves the rewrite retrieval precision of state-of-the-art baselines by 12.5–17.5% while having nearly ten times fewer parameters. © 2022 Association for Computational Linguistics.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A Comparative Assessment of State-Of-The-Art methods for Multilingual Unsupervised Keyphrase Extraction 17th

A Comparative Assessment of State-Of-The-Art Methods for Mul...

引用

17th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations (AIAI) / 6th 5G-PINE workshop / AI-BIO workshop / DAAI workshop / DARE workshop / EEAI workshop / 10th MHDW workshop

作者： Giarelis, Nikolaos Kanakaris, Nikos Karacapilidis, Nikos Univ Patras Ind Management & Informat Syst Lab MEAD Rion 26504 Greece

ISBN: (纸本)9783030791520;9783030791506;9783030791490

Keyphrase extraction is a fundamental task in information management, which is often used as a preliminary step in various information retrieval and natural language processing tasks. The main contribution of this paper lies in providing a comparative assessment of prominent multilingual unsupervised keyphrase extraction methods that build on statistical (RAKE, YAKE), graph-based (TextRank, SingleRank) and deep learning (KeyBERT) methods. For the experimentations reported in this paper, we employ well-known datasets designed for keyphrase extraction from five different natural languages (English, French, Spanish, Portuguese and Polish). We use the F1 score and a partial match evaluation framework, aiming to investigate whether the number of terms of the documents and the language of each dataset affect the accuracy of the selected methods. Our experimental results reveal a set of insights about the suitability of the selected methods in texts of different sizes, as well as the performance of these methods in datasets of different languages.

关键词： natural language processing Keyphrase extraction Unsupervised learning Deep learning graph-based models Empirical research

来源：评论

学校读者我要写书评

暂无评论

Referring Expression Comprehension: A Survey of methods and Datasets

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2021年 23卷 4426-4440页

作者： Qiao, Yanyuan Deng, Chaorui Wu, Qi Univ Adelaide Australian Inst Machine Learning Sch Comp Sci Adelaide SA 5005 Australia

Referring expression comprehension (REC) aims to localize a target object in an image described by a referring expression phrased in natural language. Different from the object detection task that queried object labels have been pre-defined, the REC problem only can observe the queries during the test. It is more challenging than a conventional computer vision problem. This task has attracted a lot of attention from both computer vision and natural language processing community, and several lines of work have been proposed, from CNN-RNN model, modular network to complex graph-based model. In this survey, we first examine the state-of-the-art by comparing modern approaches to the problem. We classify methods by their mechanism to encode the visual and textual modalities. In particular, we examine the common approach of joint embedding images and expressions to a common feature space. We also discuss modular architectures and graph-based models that interface with structured graph representation. In the second part of this survey, we review the datasets available for training and evaluating REC approaches. We then group results according to the datasets, backbone models, settings so that they can be fairly compared. Finally, we discuss promising future directions for this field, in particular the compositional referring expression comprehension that requires more reasoning steps to address.

关键词： Referring expression Vision and language Attention Mechanism Survey

来源：评论

学校读者我要写书评

暂无评论

Review of research on synonym equivalence relation mining

Review of research on synonym equivalence relation mining

引用

2023 International Conference on Intelligent Education and Intelligent Research, IEIR 2023

作者： Zhang, Zilin Yufan Li, BaiHong Zeng, Zhi Zhong Central China Normal University Department of Artificial Intelligence Education WuHan China

ISBN: (纸本)9798350342895

Synonym discovery, also known as synonym relation mining or synonym extraction, aims to identify and establish synonymous relationships between words, phrases, or sentences. The primary objective of this relationship mining is to enhance the performance of natural language processing (NLP) tasks, such as information retrieval, question-answering systems, text summarization, and machine translation. Considering that there are still numerous areas and issues awaiting further research in synonym relation mining, this paper provides a comprehensive review of the research methods employed in this field over the past two decades. The review is organized into four main categories. The first category explores the u e of language models for synonym extraction, including techniques such as word embeddings and the recent BERT model. The second category focuses on computing semantic similarity in synonym semantic spaces. The third category examines neural network-based approaches for synonym relation mining. Lastly, the fourth category delves into constructing synonym relationships based on knowledge graphs. Additionally, this paper provides an outlook and summary of potential future developments in this direction, with the aim of offering valuable guidance for future research in the field. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Heterogeneous graph Representation Learning for Short Text Classification

Hierarchical Heterogeneous Graph Representation Learning for...

引用

Conference on Empirical methods in natural language processing (EMNLP)

作者： Wang, Yaqing Wang, Song Yao, Quanming Dou, Dejing Baidu Inc Baidu Res Beijing Peoples R China Univ Virginia Dept ECE Charlottesville VA 22903 USA Tsinghua Univ Dept EE Beijing Peoples R China

ISBN: (纸本)9781955917094

Short text classification is a fundamental task in natural language processing. It is hard due to the lack of context information and labeled data in practice. In this paper, we propose a new method called SHINE, which is based on graph neural network (GNN), for short text classification. first, we model the short text dataset as a hierarchical heterogeneous graph consisting of word-level component graphs which introduce more semantic and syntactic information. Then, we dynamically learn a short document graph that facilitates effective label propagation among similar short texts. Thus, comparing with existing GNN-based methods, SHINE can better exploit interactions between nodes of the same types and capture similarities between short texts. Extensive experiments on various benchmark short text datasets show that SHINE consistently outperforms state-of-the-art methods, especially with fewer labels.(1)

关键词： graph neural networks

来源：评论

学校读者我要写书评

暂无评论

T-STAR: Truthful Style Transfer using AMR graph as Intermediate Representation

T-STAR: Truthful Style Transfer using AMR Graph as Intermedi...

引用

2022 Conference on Empirical methods in natural language processing, EMNLP 2022

作者： Jangra, Anubhav Nema, Preksha Raghuveer, Aravindan Google Research India

Unavailability of parallel corpora for training text style transfer (TST) models is a very challenging yet common scenario. Also, TST models implicitly need to preserve the content while transforming a source sentence into the target style. To tackle these problems, an intermediate representation is often constructed that is devoid of style while still preserving the meaning of the source sentence. In this work, we study the usefulness of Abstract Meaning Representation (AMR) graph as the intermediate style agnostic representation. We posit that semantic notations like AMR are a natural choice for an intermediate representation. Hence, we propose T-STAR: a model comprising of two components, text-to-AMR encoder and a AMR-to-text decoder. We propose several modeling improvements to enhance the style agnosticity of the generated AMR. To the best of our knowledge, T-STAR is the first work that uses AMR as an intermediate representation for TST. With thorough experimental evaluation we show T-STAR significantly outperforms state of the art techniques by achieving on an average 15.2% higher content preservation with negligible loss (∼3%) in style accuracy. Through detailed human evaluation with 90, 000 ratings, we also show that TSTAR has upto 50% lesser hallucinations compared to state of the art TST models. © 2022 Association for Computational Linguistics.

关键词： Semantics

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：