Information retrieval : 28th China conference, CCIR 2022, Chongqing, China, September 16-18, 2022, revised selected papers / / Yi Chang, Xiaofei Zhu (editors)

• Record Nr.: UNISA996511872103316
• Pubbl/distr/stampa: Cham, Switzerland : , : Springer, , [2023]; ©2023
• ISBN: 3-031-24755-8
• Edizione: [1st ed. 2023.]
• Descrizione fisica: 1 online resource (117 pages)
• Collana: Lecture notes in computer science ; ; Volume 13819
• Disciplina: 025.04
• Soggetti: Information retrieval
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Nota di contenuto: Intro -- Preface -- Organization -- Contents -- A Position-Aware Word-Level and Clause-Level Attention Network for Emotion Cause Recognition -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 The Definition of Emotion Cause Recognition -- 3.2 Position-Aware Word-Level and Clause-Level Attention Network for Emotion Cause Recognition -- 3.3 Model Training -- 4 Experiment -- 4.1 Experimental Settings -- 4.2 Experimental Results -- 4.3 Qualitative Analysis -- 5 Conclusion and Future Work -- References -- ID-Agnostic User Behavior Pre-training for Sequential Recommendation -- 1 Introduction -- 2 Preliminaries -- 3 Methodology -- 3.1 ID-Agnostic User Behavior Pre-training -- 3.2 Fine-Tuning for Recommendation -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Experimental Results -- 5 Related Work -- 6 Conclusion -- References -- Enhance Performance of Ad-hoc Search via Prompt Learning -- 1 Introduction -- 2 Related Work -- 2.1 Ad Hoc Search with PTM -- 2.2 Prompt Learning -- 3 Preliminary -- 3.1 Ad hoc Search -- 3.2 Prompt Learning -- 4 Methodology -- 5 Experiments -- 5.1 Dataset and Metric -- 5.2 Experimental Setup -- 5.3 Result and Analysis -- 5.4 Case Study -- 6 Conclusion -- References -- Syntax-Aware Transformer for Sentence Classification -- 1 Introduction -- 2 Syntax-Aware Transformer -- 2.1 Syntactic Subnetwork -- 2.2 Semantic Subnetwork -- 2.3 Merging Layer -- 3 Experiments -- 3.1 Datasets -- 3.2 Experimental Settings -- 3.3 ; Baseline Models -- 3.4 Results and Discussion -- 3.5 Case Study -- 4 Conclusions -- References -- Evaluation of Deep Reinforcement Learning Based Stock Trading -- 1 Introduction -- 2 Related Works -- 3 RL Modeling of Stock Trading -- 3.1 Problem Description -- 3.2 Mathematical Presentation -- 3.3 Trading Details -- 3.4 Feasibility Analysis of RL-Based Stock Trading -- 4 Experiments -- 4.1 Stock Dataset.; 4.2 Methodology -- 4.3 Results -- 5 Conclusion and Future Works -- References -- InDNI: An Infection Time Independent Method for Diffusion Network Inference -- 1 Introduction -- 2 Related Work -- 3 Problem Statement -- 4 InDNI Algorithm -- 4.1 Node Representation Learning -- 4.2 Similarity Measure -- 4.3 Filtering Candidate Node Pairs -- 4.4 Network Inference -- 5 Experiments -- 5.1 Experimental Setup -- 5.2 Results and Discussion -- 6 Conclusion and Future Work -- References -- Beyond Precision: A Study on Recall of Initial Retrieval with Neural Representations -- 1 Introduction -- 2 Related Work -- 2.1 Initial Retrieval -- 2.2 Neural Representations for IR -- 3 Our Approach -- 3.1 Symbolic Index -- 3.2 Neural Index -- 3.3 Parallel Search Scheme -- 3.4 Sequential Search Scheme -- 3.5 Discussions -- 4 Experiments -- 4.1 Baselines and Experimental Settings -- 4.2 Evaluation Methodology -- 4.3 Retrieval Performance and Analysis -- 4.4 Analysis on Retrieved Relevant Documents -- 5 Conclusions -- References -- A Learnable Graph Convolutional Neural Network Model for Relation Extraction -- 1 Introduction -- 2 Related Work -- 3 Model -- 3.1 Input Representation Layer -- 3.2 Fusion Module -- 3.3 Classification Module -- 4 Experiments -- 4.1 Datasets -- 4.2 Hyper-parameter Setting -- 4.3 Overall Performance -- 4.4 Ablation Study -- 4.5 Effect of Length of Each Part -- 5 Conclusion and Future Work -- References -- Author Index.
• Sommario/riassunto: This book constitutes the refereed proceedings of the 28th China Conference on Information Retrieval, CCIR 2022, held in Chongqing, China, in September 2022. Information retrieval aims to meet the demand of human on the Internet to obtain information quickly and accurately. The 8 full papers presented were carefully reviewed and selected from numerous submissions. The papers provide a wide range of research results in information retrieval area.