While person re-identification (Re-ID) has achieved remarkable progress in controlled laboratory settings, its widespread deployment in real-world urban surveillance remains impeded by the significant domain gaps caused by environmental dynamics and sparse camera topologies. In such operational scenarios, relying solely on visual appearance leads to severe visual ambiguity, while the continuous expansion of camera networks induces catastrophic forgetting. To bridge this “lab-to-real” gap, we present a robust, street-surveillance-oriented Re-ID solution validated across a diverse array of benchmarks. Our framework incorporates three key innovations: (1) We construct a deployable Teacher–Student framework to ensure stable feature transfer from labeled source domains to noisy target environments, enabling robust adaptation without manual supervision; (2) Addressing system sustainability, we design a diversity-preserving Dynamic Data Replay mechanism based on Farthest Point Sampling (FPS) to prevent catastrophic forgetting as the network continuously expands; (3) A Spatiotemporal Feature Fusion (STFF) module is developed to resolve visual ambiguity in sparse networks by imposing explicit physical constraints to filter out spatiotemporally infeasible candidates. Extensive evaluations on a proprietary benchmark derived from the live Hainan surveillance system and a series of mainstream datasets demonstrate that our method significantly outperforms existing approaches, offering a superior solution for practical deployment in smart city infrastructure.

Recent studies exploited Large Language Models (LLMs) to autonomously generate heuristics for solving Combinatorial Optimization Problems (COPs), by prompting LLMs to first provide search directions and then derive heuristics accordingly. However, the absence of task-specific knowledge in prompts often leads LLMs to provide unspecific search directions, obstructing the derivation of well-performing heuristics. Moreover, evaluating the derived heuristics remains resource-intensive, especially for those semantically equivalent ones, often requiring omissible resource expenditure. To enable LLMs to provide specific search directions, we propose the Hercules algorithm, which leverages our designed Core Abstraction Prompting (CAP) method to abstract the core components from elite heuristics and incorporate them as prior knowledge in prompts. We theoretically prove the effectiveness of CAP in reducing unspecificity and provide empirical results in this work. To reduce computing resources required for evaluating the derived heuristics, we propose few-shot Performance Prediction Prompting (PPP), a first-of-its-kind method for the Heuristic Generation (HG) task. PPP leverages LLMs to predict the fitness values of newly derived heuristics by analyzing their semantic similarity to previously evaluated ones. We further develop two tailored mechanisms for PPP to enhance predictive accuracy and determine unreliable predictions, respectively. The use of PPP makes Hercules more resource-efficient and we name this variant Hercules-P. Extensive experiments across four HG tasks, five COPs, and eight LLMs demonstrate that Hercules outperforms the state-of-the-art LLM-based HG algorithms, while Hercules-P excels at minimizing required computing resources. In addition, we illustrate the effectiveness of CAP, PPP, and the other proposed mechanisms by conducting relevant ablation studies.

Open relation extraction is the task of extracting open-domain relation facts from natural language sentences. Existing works either utilize distant-supervised annotations to train a supervised classifier over pre-defined relations, or adopt unsupervised methods with additional dependency on external assumptions. However, these works can only obtain information signals from limited existing knowledge bases or datasets. In this work, we propose a self-supervised framework namedWeb-SelfORE, which exploits self-supervised signals by requiring a large pretrained language model to extensively read real-world relevant documents from the web, and obtain contextualized relational features by mixing contextualized representations of entities from different documents. We perform adaptive clustering on contextualized relational features and bootstrap the self-supervised signals by improving contextualized features in relation classification. We additionally compare the effectiveness of self-supervisions brought by different document sources, and introduce relevance and redundancy evaluation metrics to obtain higher-quality self-supervisions. Experimental results on four public datasets show the effectiveness and robustness ofWeb-SelfOREon open-domain relation extraction task when comparing with competitive baselines.

Low-resource relation extraction (LRE) aims to extract potential relations from limited labeled corpus to handle the problem of scarcity of human annotations. Previous works mainly consist of two categories of methods: (1) Self-training methods, which improve themselves through the models' predictions, thus suffering from confirmation bias when the predictions are wrong. (2) Self-ensembling methods, which learn task-agnostic representations, therefore, generally do not work well for specific tasks. In our work, we propose a novel LRE architecture named SelfLRE, which leverages two complementary modules, one module uses self-training to obtain pseudo-labels for unlabeled data, and the other module uses self-ensembling learning to obtain the task-agnostic representations, and leverages the existing pseudo-labels to refine the better task-specific representations on unlabeled data. The two models are jointly trained through multi-task learning to iteratively improve the effect of LRE task. Experiments on three public datasets show that SelfLRE achieves 1.81% performance gain over the SOTA baseline. Source code is available at: https://github.com/THU-BPM/SelfLRE.

As social media platforms are evolving from text-based forums into multi-modal environments, the nature of misinformation in social media is also transforming accordingly. Misinformation spreaders have recently targeted contextual connections between the modalities e.g., text and image. However, existing datasets for rumor detection mainly focus on a single modality i.e., text. To bridge this gap, we construct MR2, a multimodal multilingual retrieval-augmented dataset for rumor detection. The dataset covers rumors with images and texts, and provides evidence from both modalities that are retrieved from the Internet. Further, we develop established baselines and conduct a detailed analysis of the systems evaluated on the dataset. Extensive experiments show that MR2 will provide a challenging testbed for developing rumor detection systems designed to retrieve and reason over social media posts. Source code and data are available at: https://github.com/THU-BPM/MR2.

Real-world fact verification task aims to verify the factuality of a claim by retrieving evidence from the source document. The quality of the retrieved evidence plays an important role in claim verification. Ideally, the retrieved evidence should be faithful (reflecting the model's decision-making process in claim verification) and plausible (convincing to humans), and can improve the accuracy of verification task. Although existing approaches leverage the similarity measure of semantic or surface form between claims and documents to retrieve evidence, they all rely on certain heuristics that prevent them from satisfying all three requirements. In light of this, we propose a fact verification model named ReRead to retrieve evidence and verify claim that: (1) Train the evidence retriever to obtain interpretable evidence (i.e., faithfulness and plausibility criteria); (2) Train the claim verifier to revisit the evidence retrieved by the optimized evidence retriever to improve the accuracy. The proposed system is able to achieve significant improvements upon best-reported models under different settings.

The generalizability to new databases is of vital importance to Text-to-SQL systems which aim to parse human utterances into SQL statements. Existing works achieve this goal by leveraging the exact matching method to identify the lexical matching between the question words and the schema items. However, these methods fail in other challenging scenarios, such as the synonym substitution in which the surface form differs between the corresponding question words and schema items. In this paper, we propose a framework named ISESL-SQL to iteratively build a semantic enhanced schema-linking graph between question tokens and database schemas. First, we extract a schema linking graph from PLMs through a probing procedure in an unsupervised manner. Then the schema linking graph is further optimized during the training process through a deep graph learning method. Meanwhile, we also design an auxiliary task called graph regularization to improve the schema information mentioned in the schema-linking graph. Extensive experiments on three benchmarks demonstrate that ISESL-SQL could consistently outperform the baselines and further investigations show its generalizability and robustness.

Prediction over event sequences is critical for many real-world applications in Information Retrieval and Natural Language Processing. Future Event Generation (FEG) is a challenging task in event sequence prediction because it requires not only fluent text generation but also commonsense reasoning to maintain the logical coherence of the entire event story. In this paper, we propose a novel explainable FEG framework, Coep. It highlights and integrates two types of event knowledge, sequential knowledge of direct event-event relations and inferential knowledge that reflects the intermediate character psychology between events, such as intents, causes, reactions, which intrinsically pushes the story forward. To alleviate the knowledge forgetting issue, we design two modules, IM and GM, for each type of knowledge, which are combined via prompt tuning. First, IM focuses on understanding inferential knowledge to generate commonsense explanations and provide a soft prompt vector for GM. We also design a contrastive discriminator for better generalization ability. Second, GM generates future events by modeling direct sequential knowledge with the guidance of IM. Automatic and human evaluation demonstrate that our approach can generate more coherent, specific, and logical future events.

Text classification in low-resource languages (eg Thai) is of great practical value for some information retrieval applications (eg sentiment-analysis-based restaurant recommendation). Due to lacking large-scale corpus for learning comprehensive text representation, bilingual text classification which borrows the linguistics knowledge from a rich-resource language becomes a promising solution. Despite the success of bilingual methods, they largely ignore another source of semantic information---the writing system. Noting that most low-resource languages are phonographic languages, we argue that a logographic language (eg Chinese) can provide helpful information for improving some phonographic languages' text classification, since a logographic character (ie logogram) could represent a sememe or a whole concept, not only a phoneme or a sound. In this paper, by using a phonographic labeled corpus and its machine-translated logographic corpus both, we devise a framework to explore the central theme of utilizing logograms as a "semantic detection assistant''. Specifically, from a logographic labeled corpus, we first devise a statistical-significance-based module to pick out informative text pieces. To represent them and further reduce the effects of translation errors, our approach is equipped with Gaussian embedding whose covariances serve as reliable signals of translation errors. For a test document, all seeds' Gaussian representations are used to convolute the document and produce a logographic embedding, before being fused with its phonographic embedding for final prediction. Extensive experiments validate the effectiveness of our approach and further investigations show its generalizability and robustness.

Sharing process models on the web has emerged as a common practice. Users can collect and share their experimental process models with others. However, some users always feel confused about the shared process models for lack of necessary guidelines or instructions. Therefore, several process translators have been proposed to explain the semantics of process models in natural language (NL). We find that previous studies suffer from information loss and generate semantically erroneous descriptions that diverge from original model behaviors. In this paper, we propose a novel process translator named BePT (Behavior-based Process Translator) based on the encoder-decoder paradigm, encoding a process model into a middle representation and decoding the representation into NL descriptions. Our theoretical analysis demonstrates that BePT satisfies behavior correctness, behavior completeness and description minimality. The qualitative and quantitative experiments show that BePT outperforms the state-of-the-art baselines.

The variational neural models have achieved significant progress in dialogue generation. They are of encoder-decoder architecture, with stochastic latent variables learned at the utterance level. However, latent variables are usually approximated by factorized-form distributions, the value space of which is too large relative to latent features to be encoded, leading to the sparsity problem. As a result, little useful information is carried in latent representations, and generated responses tend to be non-committal and meaningless. To address it, we initially propose the Latent-Constrained Variational Neural Dialogue Model (LC-VNDM). It follows variational neural dialogue framework, with an utterance encoder, a context encoder and a response decoder hierarchically organized. Particularly, LC-VNDM uses a hierarchically-structured variational distribution form, which considers inter-dependencies between latent variables. Thus it defines a constrained latent value space, and prevents latent global features from being diluted. Therefore, latent representations sampled from it would carry richer global information to facilitate the decoding, generating meaningful responses. We conduct extensive experiments on three datasets using automatic evaluation and human evaluation. Experiments prove that LC-VNDM significantly outperforms the state-of-the-arts and can generate information-richer responses by learning a better-quality latent space.

Event sequence prediction has wide applications on economics, electronic health and social media monitoring. Accurate prediction of event sequences can help provide better service to customers and prevent risks. Recent works try to address the problem aiming at learning the impact of past events on the future events using deep learning methods. Such works often take the past event sequences as input and model the self-change transformations of the events, and few of them concerned the effect of event attributes. We propose an RNN-based predictive model to encode multiple attributes as attached information of the event for predicting next event and its attributes given past sequences. To learn how important each attribute is for the event, we design a component modulator to customize weights for representations of the event and its attributes. The more important the information is, the relevant weight will be higher. Finally, the prediction of next event and its attributes are conducted simultaneously with a different modulator for each predictive task. The performance of the proposed model was evaluated on 5 real-life datasets, containing two different types of event logs. The results show that our model outperforms the baselines and the state-of-the-art, not only on the prediction of next event and its attributes but also the generation of event sequence suffix.

Deep Generative Models (DGMs) are able to extract high-level representations from massive unlabeled data and are explainable from a probabilistic perspective. Such characteristics favor sequence modeling tasks. However, it still remains a huge challenge to model sequences with DGMs. Unlike real-valued data that can be directly fed into models, sequence data consist of discrete elements and require being transformed into certain representations first. This leads to the following two challenges. First, high-level features are sensitive to small variations of inputs as well as the way of representing data. Second, the models are more likely to lose long-term information during multiple transformations. In this paper, we propose a Hierarchical Deep Generative Model With Dual Memory to address the two challenges. Furthermore, we provide a method to efficiently perform inference and learning on the model. The proposed model extends basic DGMs with an improved hierarchically organized multi-layer architecture. Besides, our model incorporates memories along dual directions, respectively denoted as broad memory and deep memory. The model is trained end-to-end by optimizing a variational lower bound on data log-likelihood using the improved stochastic variational method. We perform experiments on several tasks with various datasets and obtain excellent results. The results of language modeling show our method significantly outperforms state-of-the-art results in terms of generative performance. Extended experiments including document modeling and sentiment analysis, prove the high-effectiveness of dual memory mechanism and latent representations. Text random generation provides a straightforward perception for advantages of our model.

Process mining links traditional model-driven Business Process Management and data mining by means of deriving knowledge from event logs to improve operational business processes. As an impact factor of the quality of process mining results, the degree of completeness of the given event log should be necessarily measured. In this paper an approach is proposed in the context of mining control-flow dependencies to evaluate the local completeness of an event log without knowing any information about the original process model. Experiment results show that the proposed approach works robustly and gives better estimation than approaches available.

In workflow management systems (WFMSs), time management plays an essential role in controlling the lifecycle of business processes. Especially, run-time analysis of time constraints is necessary to help process manger proactively detect possible deadline violations and appropriately handle these violations. Traditional time constraint analyses either present deterministic results which are too restrictive in highly uncertain workflow processes, or only consider static analysis at workflow build-time. For such an issue, this paper proposes a dynamic approach for analyzing time constraints during process execution. To be specific, based on a Petri-net-extended stochastic model, this approach first analyzes activity instances’ continuous probabilities of satisfying time constraints when a process instance is initiated. Afterwards, during the execution of this process instance, the approach dynamically updates these probabilities whenever an activity instance is completed. Moreover, an example process instance in real-world WFMSs shows the practicality of our approach.