Information Processing & Management最新文献

As the volume of submitted papers continues to rise, ensuring a fair and accurate assignment of manuscripts to reviewers has become increasingly critical for academic conference organizers. Given the paper-reviewer similarity scores, this study introduces the Balanced and Fair Reviewer Assignment Problem (BFRAP), which aims to maximize the overall similarity score (efficiency) and the minimum paper score (fairness) subject to coverage, load balance, and fairness constraints. Addressing the challenges posed by these constraints, we conduct a theoretical investigation into the threshold conditions for the problem’s feasibility and optimality. To facilitate this investigation, we establish a connection between BFRAP, defined over $m$ reviewers, and the Equitable m-Coloring Problem. Building on this theoretical foundation, we propose FairColor, an algorithm designed to retrieve fair and efficient assignments. We compare FairColor to Fairflow and FairIR, two state-of-the-art algorithms designed to find fair assignments under similar constraints. Empirical experiments were conducted on four real and two synthetic datasets involving (paper, reviewer) matching scores ranging from (100,100) to (10124,5880). Results demonstrate that FairColor is able to find efficient and fair assignments quickly compared to Fairflow and FairIR. Notably, in the largest instance involving 10,124 manuscripts and 5680 reviewers, FairColor retrieves fair and efficient assignments in just 67.64 s. This starkly contrasts both other methods, which require significantly longer computation times (45 min for Fairflow and 3 h 24 min for FairIR), even on more powerful machines. These results underscore FairColor as a promising alternative to current state-of-the-art assignment techniques.

Despite recent advances in large language models (LLMs), the best effectiveness in information extraction (IE) is still achieved by fine-tuned models, hence the need for manually annotated datasets to train them. However, collecting human annotations for IE, especially for scientific IE, where expert annotators are often required, is expensive and time-consuming. Another issue widely discussed in the IE community is noisy annotations. Mislabelled training samples can hamper the effectiveness of trained models. In this paper, we propose a solution to alleviate problems originating from the high cost and difficulty of the annotation process. Our method distinguishes clean training samples from noisy samples and then employs weighted weakly supervised learning (WWSL) to leverage noisy annotations. Evaluation of Named Entity Recognition (NER) and Relation Classification (RC) tasks in Scientific IE demonstrates the substantial impact of detecting clean samples. Experimental results highlight that our method, utilising clean and noisy samples with WWSL, outperforms the baseline RoBERTa on NER (＋4.28, ＋4.59, ＋29.27, and ＋5.21 gain for the ADE, SciERC, STEM-ECR, and WLPC datasets, respectively) and the RC (＋6.09 and ＋4.39 gain for the SciERC and WLPC datasets, respectively) tasks. Comprehensive analyses of our method reveal its advantages over state-of-the-art denoising baseline models in scientific NER. Moreover, the framework is general enough to be adapted to different NLP tasks or domains, which means it could be useful in the broader NLP community.

Table-based fact verification focuses on determining the truthfulness of statements by cross-referencing data in tables. This task is challenging due to the complex interactions inherent in table structures. To address this challenge, existing methods have devised a range of specialized models. Although these models demonstrate good performance, they still exhibit limited sensitivity to essential variations in information relevant to reasoning within both statements and tables, thus learning spurious patterns and leading to potentially unreliable outcomes. In this work, we propose a novel approach named Multi-Aspect Adversarial Contrastive Learning (Macol), aimed at enhancing the accuracy and robustness of table-based fact verification systems under the premise of resource efficiency. Specifically, we first extract pivotal logical reasoning clues to construct positive and adversarial negative instances for contrastive learning. We then propose a new training paradigm that introduces a contrastive learning objective, encouraging the model to recognize noise invariance between original and positive instances while also distinguishing logical differences between original and negative instances. Extensive experimental results on three widely studied datasets TABFACT, INFOTABS and SEM-TAB-FACTS demonstrate that Macol achieves state-of-the-art performance on benchmarks across various backbone architectures, with accuracy improvements reaching up to 5.4%. Furthermore, Macol exhibits significant advantages in robustness and low-data resource scenarios, with improvements of up to 8.2% and 9.1%. It is worth noting that our method achieves comparable or even superior performance while being more resource-efficient compared to approaches that employ specific additional pre-training or utilize large language models (LLMs).

Deep learning has driven research in object detection and achieved proud results. Despite its significant advancements in object detection, small object detection still struggles with low recognition rates and inaccurate positioning, primarily attributable to their miniature size. The location deviation of small objects induces severe feature misalignment, and the disequilibrium between classification and regression tasks hinders accurate recognition. To address these issues, we propose a Dynamic Feature Focusing Network (DFFN), which contains a duo of crucial modules: Visual Perception Enhancement Module (VPEM) and Task Association Module (TAM). Drawing upon the deformable convolution and attention mechanism, the VPEM concentrates on sparse key features and perceives the misalignment via positional offset. We aggregate multi-level features at identical spatial locations via layer average operation for learning a more discriminative representation. Incorporating class alignment and bounding box alignment parts, the TAM promotes classification ability, refines bounding box regression, and facilitates the joint learning of classification and localization. We conduct diverse experiments, and the proposed method considerably enhances the small object detection performance on four benchmark datasets of MS COCO, VisDrone, VOC, and TinyPerson. Our method has improved by 3.4 and 2.2 in mAP and APs, making solid improvements on COCO. Compared to other classic detection models, DFFN exhibits a high level of competitiveness in precision.

Oracle bone characters (OBCs) are ancient ideographs for divination and memorization, as well as first-hand evidence of ancient Chinese culture. The detection of OBC is the premise of advanced studies and was mainly done by authoritative experts in the past. Deep learning techniques have great potential to facilitate OBC detection, but the high annotation cost of OBC brings the scarcity of labeled data, hindering its application. This paper proposes a novel OBC detection framework called OBCTeacher based on semi-supervised learning (SSL) to resist labeled data scarcity. We first construct a large-scale OBC detection dataset. Through investigation, we find that spatial mismatching and class imbalance problems lead to decreased positive anchors and biased predictions, affecting the quality of pseudo labels and the performance of OBC detection. To mitigate the spatial mismatching problem, we introduce a geometric-priori-based anchor assignment strategy and a heatmap polishing procedure to increase positive anchors and improve the quality of pseudo labels. As for the class imbalance problem, we propose a re-weighting method based on estimated class information and a contrastive anchor loss to achieve prioritized learning on different OBC classes and better class boundaries. We evaluate our method by using only a small portion of labeled data while using the remaining data as unlabeled and all labeled data with extra unlabeled data. The results demonstrate the effectiveness of our method compared with other state-of-the-art methods by superior performance and significant improvements of an average of 11.97 in $A{P}_{50:95}$ against the only supervised baseline. In addition, our method achieves comparable performance using only 20% of labeled data to the fully-supervised baseline using 100% of labeled data, demonstrating that our method significantly reduces the dependence on labeled data for OBC detection.

As a crucial step in promoting data sharing, data trading can stimulate the development of the data economy. However, the current data trading market primarily focuses on satisfying data owners' interests, overlooking the demands of data requesters. Ignoring the demands of data requesters may lead to a loss of market competitiveness, customer loss, and missed business opportunities while damaging reputation and innovation capabilities. Therefore, in this paper, we introduce a novel pricing mechanism named Get By How Much You Pay (GHMP) based on compressed sensing technology and game theory to address pricing problems according to data requesters' demands. This scheme employs a dictionary matrix as the sparse basis matrix in compressed sensing. The quality of this matrix directly affects the precision with which the requester can reconstruct the data. If the requester requires higher-precision data, the corresponding payment will also increase accordingly so as to realize the pricing method based on the requester's demands. A game pricing method is proposed to address the final pricing and purchasing issues between the data requester and the data owner by utilizing an authorized smart contract as an intermediary. As an entity participating in the game, the smart contract can only receive a higher transaction fee if it successfully assists the data requester and data owner in completing the pricing. Therefore, it strives to establish more reasonable prices for both parties during the trading process to obtain profits. The experimental results demonstrate that this game-based approach assists the data requester and owner in achieving optimal data pricing, thereby satisfying the maximization of interests for both parties.

Large teams are known to be more likely to publish highly cited papers, while small teams are known to be better at publishing highly disruptive papers. However, there is a lack of adequate theoretical understanding of the mechanisms by which scientific collaboration among researchers is related to the scientific impact of their papers. We investigated the mechanisms more closely by focusing on the interaction of inter-organizational diversity and team size in the process of team formation and knowledge dissemination. We analyzed 12,010,102 Web of Science papers and examined how inter-organizational diversity is associated with the relationship of team size with disruption and citations. As a result, we found that not only small teams, but also large teams with great inter-organizational diversity were able to disrupt science and technology effectively. We also found that large teams with greater inter-organizational diversity were more likely to produce highly cited papers. Our findings are robust and consistently observed regardless of publication year, team size, the number of references, and the degree of multidisciplinarity. These results have significant implications for researchers in selecting collaborators to achieve greater impact and for improving the qualitative efficiency of public research investments.

Purpose

The serious information overload problem of MOOCs videos decreases the learning efficiency of the students and the utilization rate of the videos. There are two problems worthy of attention for the matrix factorization (MF)-based video learning resource recommender systems. Those methods suffer from the sparsity problem of the user-item rating matrix, while side information about user and item is seldom used to guide the learning procedure of the MF.

Method

To address those two problems, we proposed a new MOOCs video resource recommender LSMFERLI based on Low-rank and Sparse Matrix Factorization (LSMF) with the guidance of the inter-Entity Relations and intra-entity Latent Information of the students and videos. Firstly, we construct the inter-entity relation matrices and intra-entity latent preference matrix for the students. Secondly, we construct the inter-entity relation matrices and intra-entity affinity matrix for the videos. Lastly, with the guidance of the inter-entity relation and intra-entity affinity matrices of the students and videos, the student-video rating matrix is factorized into a low-rank matrix and a sparse matrix by the alternative iteration optimization scheme.

Conclusions

Experimental results on dataset MOOCcube indicate that LSMFERLI outperforms 7 state-of-the-art methods in terms of the HR@K and NDCG@K(K = 5,10,15) indicators increased by an average of 20.6 % and 21.0 %, respectively.

Identifying scientific disruption is consistently recognized as challenging, and more so is to predict it. We suggest that better predictions are hindered by the inability to integrate multidimensional information and the limited scalability of existing methods. This paper develops a framework based on graph signal processing (GSP) to predict scientific disruption, achieving an average AUC of about 80 % on benchmark datasets, surpassing the performance of prior methods by 13.6 % on average. The framework is unified, adaptable to any type of information, and scalable, with the potential for further enhancements using technologies from GSP. The intuition of this framework is: scientific disruption is characterized by leading to dramatic changes in scientific evolution, which is recognized as a complex system represented by a graph, and GSP is a technique that specializes in analyzing data on graph structures; thus, we argue that GSP is well-suited for modeling scientific evolution and predicting disruption. Based on this proposed framework, we proceed with disruption predictions. The content, context, and (citation) structure information is respectively defined as graph signals. The total variations of these graph signals, which measure the evolutionary amplitude, are the main predictors. To illustrate the unity and scalability of our framework, altmetrics data (online mentions of the paper) that seldom considered previously is defined as graph signal, and another indicator, the dispersion entropy of graph signal (measuring chaos of scientific evolution), is used for predicting respectively. Our framework also provides advantages of interpretability for a better understanding on scientific disruption. The analysis indicates that the scientific disruption not only results in dramatic changes in the knowledge content, but also in context (e.g., journals and authors), and will lead to chaos in subsequent evolution. At last, several practical future directions for disruption predictions based on the framework are proposed.

Topic evolution has been studied extensively in the field of the science of science. This study first analyzes topic evolution pattern from topics’ semantic consistency in the semantic vector space, and explore its possible causes. Specifically, we extract papers in the computer science field from Microsoft Academic Graph as our dataset. We propose a novel method for encoding a topic with numerous Contextualized Word Embeddings (CWE), in which the title and abstract fields of papers studying the topic is taken as its context. Subsequently, we employ three geometric metrics to analyze topics’ semantic consistency over time, from which the influence of the anisotropy of CWE is excluded. The K-Means clustering algorithm is employed to identify four general evolution patterns of semantic consistency, that is, semantic consistency increases (IM), decreases (DM), increases first and then decreases (Inverted U-shape), and decreases first and then increases (U-shape). We also find that research methods tend to show DM and U-shape, but research questions tend to be IM and Inverted U-shape. Finally, we further utilize the regression analysis to explore whether and, if so, how a series of key features of a topic affect its semantic consistency. Importantly, semantic consistency of a topic varies inversely with the semantic similarity between the topic and other topics. Overall, this study sheds light on the evolution law of topics, and helps researchers to understand these patterns from a geometric perspective.