Journal of Intelligent Information Systems最新文献

Abstract

Multi-modal recommendation using multi-modal features (e.g., image and text features) has received significant attention and has been shown to have more effective recommendation. However, there are currently the following problems with multi-modal recommendation: (1) Multi-modal recommendation often handle individual modes’ raw data directly, leading to noise affecting the model’s effectiveness and the failure to explore interconnections between modes; (2) Different users have different preferences. It’s impractical to treat all modalities equally, as this could interfere with the model’s ability to make recommendation. To address the above problems, this paper proposes a Multi-modal recommendation model with cross-modal correction (CMC-MMR). Firstly, in order to reduce the effect of noise in the raw data and to take full advantage of the relationships between modes, we designed a cross-modal correction module to denoise and correct the modes using a cross-modal correction mechanism; Secondly, the similarity between the same modalities of each item is used as a benchmark to build item-item graphs for each modality, and user-item graphs with degree-sensitive pruning strategies are also built to mine higher-order information; Finally, we designed a self-supervised task to adaptively mine user preferences for modality. We conducted comparative experiments with eleven baseline models on four real-world datasets. The experimental results show that CMC-MMR improves 6.202%, 4.975% , 6.054% and 11.368% on average on the four datasets, respectively, demonstrates the effectiveness of CMC-MMR.

The formulation of structured queries over Knowledge Graphs is not an easy task. To alleviate this problem, we propose a novel interactive method for SPARQL query formulation, for enabling users (plain and advanced) to formulate gradually queries by providing examples and various kinds of positive and negative feedback, in a manner that does not pre-suppose knowledge of the query language or the contents of the Knowledge Graph. In comparison to other example-based query approaches, distinctive features of our approach is the support of negative examples, and the positive/negative feedback on the generated constraints. We detail the algorithmic aspect and we present an interactive user interface that implements the approach. The application of the model on real datasets from DBpedia (Movies, Actors) and other datasets (scientific papers), showcases the feasibility and the effectiveness of the approach. A task-based evaluation that included users that are not familiar with SPARQL, provided positive evidence that the interaction is easy-to-grasp and enabled most users to formulate the desired queries.

Question Answering Over Temporal Knowledge Graphs (TKGQA) is an important topic in question answering. TKGQA focuses on accurately understanding questions involving temporal constraints and retrieving accurate answers from knowledge graphs. In previous research, the hierarchical structure of question contexts and the constraints imposed by temporal information on different sentence components have been overlooked. In this paper, we propose a framework called “Semantic-Enhanced Reasoning Question Answering” (SERQA) to tackle this problem. First, we adopt a pretrained language model (LM) to obtain the question relation representation vector. Then, we leverage syntactic information from the constituent tree and dependency tree, in combination with Masked Self-Attention (MSA), to enhance temporal constraint features. Finally, we integrate the temporal constraint features into the question relation representation using an information fusion function for answer prediction. Experimental results demonstrate that SERQA achieves better performance on the CRONQUESTIONS and ImConstrainedQuestions datasets. In comparison with existing temporal KGQA methods, our model exhibits outstanding performance in comprehending temporal constraint questions. The ablation experiments verified the effectiveness of combining the constituent tree and the dependency tree with MSA in question answering.

Medical question-answering systems require the ability to extract accurate, concise, and comprehensive answers. They will better comprehend the complex text and produce helpful answers if they can reason on the explicit constraints described in the question’s textual context and the implicit, pertinent knowledge of the medical world. Integrating Knowledge Graphs (KG) with Language Models (LMs) is a common approach to incorporating structured information sources. However, effectively combining and reasoning over KG representations and language context remains an open question. To address this, we propose the Knowledge Infused Medical Question Answering system (KIMedQA), which employs two techniques viz. relevant knowledge graph selection and pruning of the large-scale graph to handle Vector Space Inconsistent (VSI) and Excessive Knowledge Information (EKI). The representation of the query and context are then combined with the pruned knowledge network using a pre-trained language model to generate an informed answer. Finally, we demonstrate through in-depth empirical evaluation that our suggested strategy provides cutting-edge outcomes on two benchmark datasets, namely MASH-QA and COVID-QA. We also compared our results to ChatGPT, a robust and very powerful generative model, and discovered that our model outperforms ChatGPT according to the F1 Score and human evaluation metrics such as adequacy.

Abstract

Detecting deviant traces in business process logs is crucial for modern organizations, given the harmful impact of deviant behaviours (e.g., attacks or faults). However, training a Deviance Prediction Model (DPM) by solely using supervised learning methods is impractical in scenarios where only few examples are labelled. To address this challenge, we propose an Active-Learning-based approach that leverages multiple DPMs and a temporal ensembling method that can train and merge them in a few training epochs. Our method needs expert supervision only for a few unlabelled traces exhibiting high prediction uncertainty. Tests on real data (of either complete or ongoing process instances) confirm the effectiveness of the proposed approach.

A Knowledge Graph-based Question Answering (KGQA) system attempts to answer a given natural language question using a knowledge graph (KG) rather than from text data. The current KGQA methods attempt to determine whether there is an explicit relationship between the entities in the question and a well-structured relationship between them in the KG. However, such strategies are difficult to build and train, limiting their consistency and versatility. The use of language models such as BERT has aided in the advancement of natural language question answering. In this paper, we present a novel Graph Neural Network(GNN) based approach with relevance scoring for improving KGQA. GNNs use the weight of nodes and edges to influence the information propagation while updating the node features in the network. The suggested method comprises subgraph construction, weighing of nodes and edges, and pruning processes to obtain meaningful answers. BERT-based GNN is used to build subgraph node embeddings. We tested the influence of weighting for both nodes and edges and observed that the system performs better for weighted graphs than unweighted graphs. Additionally, we experimented with several GNN convolutional layers and obtainined improved results by combining GENeralised Graph Convolution (GENConv) with node weights for simple questions. Extensive testing on benchmark datasets confirmed the effectiveness of the proposed model in comparison to state-of-the-art KGQA systems.

Abstract

This paper analyses Twitter data to detect the political lean of a profile by extracting and classifying sentiments expressed through tweets. The work utilizes natural language processing, augmented with sentiment analysis algorithms and machine learning techniques, to classify specific keywords. The proposed methodology initially performs data pre-processing, followed by multi-aspect sentiment analysis for computing the sentiment score of the extracted keywords, for precisely classifying users into various clusters based on similarity score with respect to a sample user in each cluster. The proposed technique also predicts the sentiment of a profile towards unknown keywords and gauges the bias of an unidentified user towards political events or social issues. The proposed technique was tested on Twitter dataset with 1.72 million tweets taken from over 10,000 profiles and was able to successfully identify the political leniency of the user profiles with 99% confidence level, and also on a synthetic dataset with 2500 tweets, where the predicted accuracy and F1 score were 0.99 and 0.985 respectively, and 0.97 and 0.975 when neutral users were also considered for classification. The paper could also identify the impact of political decisions on various clusters, by analyzing the shift in the number of users belonging to the different clusters.

Knowledge Graphs (KGs) have already proven their strength as a source of high-quality information for different tasks such as data integration, search, text summarization, and personalization. Another prominent research field that has been benefiting from the adoption of KGs is that of Recommender Systems (RSs). Feeding a RS with data coming from a KG improves recommendation accuracy, diversity, and novelty, and paves the way to the creation of interpretable models that can be used for explanations. This possibility of combining a KG with a RS raises the question whether such an addition can be performed in a plug-and-play fashion – also with respect to the recommendation domain – or whether each combination needs a careful evaluation. To investigate such a question, we consider all possible combinations of (i) three recommendation tasks (books, music, movies); (ii) three recommendation models fed with data from a KG (and in particular, a semantics-aware deep learning model, that we discuss in detail), compared with three baseline models without KG addition; (iii) two main encyclopedic KGs freely available on the Web: DBpedia and Wikidata. Supported by an extensive experimental evaluation, we show the final results in terms of accuracy and diversity of the various combinations, highlighting that the injection of knowledge does not always pay off. Moreover, we show how the choice of the KG, and the form of data in it, affect the results, depending on the recommendation domain and the learning model.

Abstract

This paper tackles the critical challenge of detecting and mitigating unintended political bias in offensive meme detection. Political memes are a powerful tool that can be used to influence public opinion and disrupt voters’ mindsets. However, current visual-linguistic models for offensive meme detection exhibit unintended bias and struggle to accurately classify non-offensive and offensive memes. This can harm the fairness of the democratic process either by targeting minority groups or promoting harmful political ideologies. With Hindi being the fifth most spoken language globally and having a significant number of native speakers, it is essential to detect and remove Hindi-based offensive memes to foster a fair and equitable democratic process. To address these concerns, we propose three debiasing techniques to mitigate the overrepresentation of majority group perspectives while addressing the suppression of minority opinions in political discourse. To support our approach, we curate a comprehensive dataset called Pol_Off_Meme, designed especially for the Hindi language. Empirical analysis of this dataset demonstrates the efficacy of our proposed debiasing techniques in reducing political bias in internet memes, promoting a fair and equitable democratic environment. Our debiased model, named (DRTIM^{Adv}_{Att}) , exhibited superior performance compared to the CLIP-based baseline model. It achieved a significant improvement of +9.72% in the F1-score while reducing the False Positive Rate Difference (FPRD) by -16% and the False Negative Rate Difference (FNRD) by -14.01%. Our efforts strive to cultivate a more informed and inclusive political discourse, ensuring that all opinions, irrespective of their majority or minority status, receive adequate attention and representation.

Providing rich and accurate metadata for indexing media content is a crucial problem for all the companies offering streaming entertainment services. These metadata are commonly employed to enhance search engine results and feed recommendation algorithms to improve the matching with user interests. However, the problem of labeling multimedia content with informative tags is challenging as the labeling procedure, manually performed by domain experts, is time-consuming and prone to error. Recently, the adoption of AI-based methods has been demonstrated to be an effective approach for automating this complex process. However, developing an effective solution requires coping with different challenging issues, such as data noise and the scarcity of labeled examples during the training phase. In this work, we address these challenges by introducing a Transformer-based framework for multi-modal multi-label classification enriched with model prediction explanation capabilities. These explanations can help the domain expert to understand the system’s predictions. Experimentation conducted on two real test cases demonstrates its effectiveness.