检索结果-内蒙古大学图书馆

GERE: Generative Evidence Retrieval for Fact Verification

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Jiangui Zhang, Ruqing Guo, Jiafeng Fan, Yixing Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China

Fact verification (FV) is a challenging task which aims to verify a claim using multiple evidential sentences from trustworthy corpora, e.g., Wikipedia. Most existing approaches follow a three-step pipeline framework, including document retrieval, sentence retrieval and claim verification. High-quality evidences provided by the first two steps are the foundation of the effective reasoning in the last step. Despite being important, high-quality evidences are rarely studied by existing works for FV, which often adopt the off-the-shelf models to retrieve relevant documents and sentences in an "index-retrieve-then-rank" fashion. This classical approach has clear drawbacks as follows: i) a large document index as well as a complicated search process is required, leading to considerable memory and computational overhead;ii) independent scoring paradigms fail to capture the interactions among documents and sentences in ranking;iii) a fixed number of sentences are selected to form the final evidence set. In this work, we propose GERE, the first system that retrieves evidences in a generative fashion, i.e., generating the document titles as well as evidence sentence identifiers. This enables us to mitigate the aforementioned technical issues since: i) the memory and computational cost is greatly reduced because the document index is eliminated and the heavy ranking process is replaced by a light generative process;ii) the dependency between documents and that between sentences could be captured via sequential generation process;iii) the generative formulation allows us to dynamically select a precise set of relevant evidences for each claim. The experimental results on the FEVER dataset show that GERE achieves significant improvements over the state-of-the-art baselines, with both time-efficiency and memory-efficiency. Copyright © 2022, The Authors. All rights reserved.

关键词： Efficiency

Influence maximization with ε-almost submodular threshold functions 17

学校读者我要写书评

暂无评论

Influence maximization with ε-almost submodular threshold f...

Proceedings of the 31st International Conference on Neural Information Processing Systems

作者： Qiang Li Wei Chen Xiaoming Sun Jialin Zhang CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Microsoft Research

ISBN: (纸本)9781510860964

Influence maximization is the problem of selecting k nodes in a social network to maximize their influence spread. The problem has been extensively studied but most works focus on the submodular influence diffusion models. In this paper, motivated by empirical evidences, we explore influence maximization in the non-submodular regime. In particular, we study the general threshold model in which a fraction of nodes have non-submodular threshold functions, but their threshold functions are closely upper- and lower-bounded by some submodular functions (we call them ε-almost submodular). We first show a strong hardness result: there is no l/nγ/c approximation for influence maximization (unless P = NP) for all networks with up to nγ ε-almost submodular nodes, where γ is in (0,1) and c is a parameter depending on ε. This indicates that influence maximization is still hard to approximate even though threshold functions are close to submodular. We then provide (l - ε)ℓ(1 - 1/ε) approximation algorithms when the number of ε-almost submodular nodes is ℓ. Finally, we conduct experiments on a number of real-world datasets, and the results demonstrate that our approximation algorithms outperform other baseline algorithms.

关键词：

CorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Tasks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Jiangui Zhang, Ruqing Guo, Jiafeng Liu, Yiqun Fan, Yixing Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS University of Chinese Academy of Sciences Beijing China BNRist DCST Tsinghua University Beijing China

Knowledge-intensive language tasks (KILT) usually require a large body of information to provide correct answers. A popular paradigm to solve this problem is to combine a search system with a machine reader, where the former retrieves supporting evidences and the latter examines them to produce answers. Recently, the reader component has witnessed significant advances with the help of large-scale pre-trained generative models. Meanwhile most existing solutions in the search component rely on the traditional "index-retrieve-then-rank" pipeline, which suffers from large memory footprint and difficulty in end-to-end optimization. Inspired by recent efforts in constructing model-based IR models, we propose to replace the traditional multi-step search pipeline with a novel single-step generative model, which can dramatically simplify the search process and be optimized in an end-to-end manner. We show that a strong generative retrieval model can be learned with a set of adequately designed pre-training tasks, and be adopted to improve a variety of downstream KILT tasks with further fine-tuning. We name the pre-trained generative retrieval model as CorpusBrain as all information about the corpus is encoded in its parameters without the need of constructing additional index. Empirical results show that CorpusBrain can significantly outperform strong baselines for the retrieval task on the KILT benchmark and establish new state-of-the-art downstream performances. We also show that CorpusBrain works well under zero- and low-resource settings. Copyright © 2022, The Authors. All rights reserved.

关键词： Pipelines

Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xu, Shicheng Pang, Liang Shen, Huawei Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology CAS University of Chinese Academy of Sciences Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology CAS University of Chinese Academy of Sciences Beijing China

Text matching is a fundamental technique in both information retrieval and natural language processing. Text matching tasks share the same paradigm that determines the relationship between two given texts. The relationships vary from task to task, e.g. relevance in document retrieval, semantic alignment in paraphrase identification and answerable judgment in question answering. However, the essential signals for text matching remain in a finite scope, i.e. exact matching, semantic matching, and inference matching. Ideally, a good text matching model can learn to capture and aggregate these signals for different matching tasks to achieve competitive performance, while recent state-of-the-art text matching models, e.g. Pre-trained Language Models (PLMs), are hard to generalize. It is because the end-to-end supervised learning on task-specific dataset makes model overemphasize the data sample bias and task-specific signals instead of the essential matching signals, which ruins the generalization of model to different tasks. To overcome this problem, we adopt a specialization-generalization training strategy and refer to it as Match-Prompt. In specialization stage, descriptions of different matching tasks are mapped to only a few prompt tokens. In generalization stage, text matching model explores the essential matching signals by being trained on diverse multiple matching tasks. High diverse matching tasks avoid model fitting the data sample bias on a specific task, so that model can focus on learning the essential matching signals. Meanwhile, the prompt tokens obtained in the first step are added to the corresponding tasks to help the model distinguish different task-specific matching signals, as well as to form the basis prompt tokens for a new matching task. In this paper, we consider five common text matching tasks including document retrieval, open-domain question answering, retrieval-based dialogue, paraphrase identification, and natural language inference. Exper

关键词： Information retrieval

HoloScope: Topology-and-Spike Aware Fraud Detection

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Liu, Shenghua Hooi, Bryan Faloutsos, Christos CAS Key Laboratory of Network Data Science & Technology Institute of Computing Technology Chinese Academy of Sciences Carnegie Mellon University

As online fraudsters invest more resources, including purchasing large pools of fake user accounts and dedicated IPs, fraudulent attacks become less obvious and their detection becomes increasingly challenging. Existing approaches such as average degree maximization suffer from the bias of including more nodes than necessary, resulting in lower accuracy and increased need for manual verification. Hence, we propose HoloScope, which uses information from graph topology and temporal spikes to more accurately detect groups of fraudulent users. In terms of graph topology, we introduce "contrast suspiciousness," a dynamic weighting approach, which allows us to more accurately detect fraudulent blocks, particularly low-density blocks. In terms of temporal spikes, HoloScope takes into account the sudden bursts and drops of fraudsters’ attacking patterns. In addition, we provide theoretical bounds for how much this increases the time cost needed for fraudsters to conduct adversarial attacks. Additionally, from the perspective of ratings, HoloScope incorporates the deviation of rating scores in order to catch fraudsters more accurately. Moreover, HoloScope has a concise framework and sub-quadratic time complexity, making the algorithm reproducible and scalable. Extensive experiments showed that HoloScope achieved significant accuracy improvements on synthetic and real data, compared with state-of-the-art fraud detection methods. Copyright © 2017, The Authors. All rights reserved.

关键词： Drops

Marked temporal dynamics modeling based on recurrent neural network

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Wang, Yongqing Liu, Shenghua Shen, Huawei Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

We are now witnessing the increasing availability of event stream data, i.e., a sequence of events with each event typically being denoted by the time it occurs and its mark information (e.g., event type). A fundamental problem is to model and predict such kind of marked temporal dynamics, i.e., when the next event will take place and what its mark will be. Existing methods either predict only the mark or the time of the next event, or predict both of them, yet separately. Indeed, in marked temporal dynamics, the time and the mark of the next event are highly dependent on each other, requiring a method that could simultaneously predict both of them. To tackle this problem, in this paper, we propose to model marked temporal dynamics by using a mark-specific intensity function to explicitly capture the dependency between the mark and the time of the next event. Extensive experiments on two datasets demonstrate that the proposed method outperforms state-of-the-art methods at predicting marked temporal dynamics. Copyright © 2017, The Authors. All rights reserved.

关键词： Forecasting

Algorithms of Time Series network: Approaches Reproduction and networks Topology 9

学校读者我要写书评

暂无评论

Algorithms of Time Series Network: Approaches Reproduction a...

9th International Conference on Fuzzy Systems and data Mining, FSDM 2023

作者： Wang, Li-Na Cheng, Yuan-Yuan Tan, Gui-Min Science College Inner Mongolia University of Technology Hohhot010051 China Inner Mongolian Key Lab. of Statistical Analysis Theory for Life Data and Neural Network Modeling Hohhot010051 China

ISBN: (纸本)9781643684703

network analysis methods of time series provide a new analytical framework on describing complex behaviors using sample data. Reproducibility is one of the important principles in scientific research. This work focuses on the algorithm review and reproduction of time series network. We paid special attention to the applicability and data characteristics of the five typical algorithms: visibility graph, phase space reconstruction, fluctuation mode, symbolic representation and coarsened multidimensional time series. It provides a reference and inspiration for future analysis of time series with various characteristics. Although two pioneer methods are widely applicable, while the directed weighted network established by coarsening thoughts contains more information about time series. In addition, coarseness process makes these approaches perform better for massive data analysis. It should be noted that: the process of data coarsening needs to ensure that the data characteristics of the original time series are inherited. © 2023 The authors and IOS Press.

关键词： Time series

Temporal knowledge graph reasoning based on evolutional representation learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Zixuan Jin, Xiaolong Li, Wei Guan, Saiping Guo, Jiafeng Shen, Huawei Wang, Yuanzhuo Cheng, Xueqi School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China CAS Key Lab of Network Data Science and Technology ICT CAS Beijing China Baidu Inc. Beijing China

Knowledge Graph (KG) reasoning that predicts missing facts for incomplete KGs has been widely explored. However, reasoning over Temporal KG (TKG) that predicts facts in the future is still far from resolved. The key to predict future facts is to thoroughly understand the historical facts. A TKG is actually a sequence of KGs corresponding to different timestamps, where all concurrent facts in each KG exhibit structural dependencies and temporally adjacent facts carry informative sequential patterns. To capture these properties effectively and efficiently, we propose a novel Recurrent Evolution network based on Graph Convolution network (GCN), called RE-GCN, which learns the evolutional representations of entities and relations at each timestamp by modeling the KG sequence recurrently. Specifically, for the evolution unit, a relation-aware GCN is leveraged to capture the structural dependencies within the KG at each timestamp. In order to capture the sequential patterns of all facts in parallel, the historical KG sequence is modeled auto-regressively by the gate recurrent components. Moreover, the static properties of entities such as entity types, are also incorporated via a static graph constraint component to obtain better entity representations. Fact prediction at future timestamps can then be realized based on the evolutional entity and relation representations. Extensive experiments demonstrate that the RE-GCN model obtains substantial performance and efficiency improvement for the temporal reasoning tasks on six benchmark datasets. Especially, it achieves up to 11.46% improvement in MRR for entity prediction with up to 82 times speedup comparing to the state-of-the-art baseline. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

Beyond low-frequency information in graph convolutional networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Bo, Deyu Wang, Xiao Shi, Chuan Shen, Huawei Beijing University of Posts and Telecommunications China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

Graph neural networks (GNNs) have been proven to be effective in various network-related tasks. Most existing GNNs usually exploit the low-frequency signals of node features, which gives rise to one fundamental question: is the low-frequency information all we need in the real world applications? In this paper, we first present an experimental investigation assessing the roles of low-frequency and high-frequency signals, where the results clearly show that exploring low-frequency signal only is distant from learning an effective node representation in different scenarios. How can we adaptively learn more information beyond low-frequency information in GNNs? A well-informed answer can help GNNs enhance the adaptability. We tackle this challenge and propose a novel Frequency Adaptation Graph Convolutional networks (FAGCN) with a self-gating mechanism, which can adaptively integrate different signals in the process of message passing. For a deeper understanding, we theoretically analyze the roles of low-frequency signals and high-frequency signals on learning node representations, which further explains why FAGCN can perform well on different types of networks. Extensive experiments on six real-world networks validate that FAGCN not only alleviates the over-smoothing problem, but also has advantages over the state-of-the-arts. Copyright © 2021, The Authors. All rights reserved.

关键词： Graph neural networks