Template-based approaches have advanced Event Argument Extraction (EAE) by formulating it as a structured prediction problem. However, existing methods mainly rely on either fixed manually designed templates, which suffer from template under-matching in diverse contexts, or exhaustive enumeration of template permutations, incurring prohibitively high computational cost. Moreover, they often overlook the semantic heterogeneity across events. To address these challenges, we propose ATSR, an Adaptive Template Selection and Role-Aware Routing framework for document-level multi-event EAE, integrating an Adaptive Multi-structure Template Selection (AMSTS) module and a Role-Aware Mixture-of-Experts (RAMoE) module. Specifically, AMSTS leverages a set of pre-defined multi-structure templates for each event type and adaptively selects the most compatible one for each event based on learnable weights conditioned on trigger representations. The RAMoE operates over template-aligned slots and routes each role to specialized experts for event semantic modeling. Extensive experiments on three benchmark datasets demonstrate that ATSR achieves state-of-the-art performance with competitive efficiency, while remaining effective in few-shot settings.

Temporal Knowledge Graph (TKG) reasoning seeks to predict future missing facts from historical evidence. While diffusion models (DM) have recently gained attention for their ability to capture complex predictive distributions, two gaps remain: (i) the generative path is conditioned only on positive evidence, overlooking informative negative context, and (ii) training objectives are dominated by cross-entropy ranking, which improves candidate ordering but provides little supervision over the calibration of the denoised embedding. To bridge this gap, we introduce Negative-Aware Diffusion model for TKG Extrapolation (NADEx). Specifically, NADEx encodes subject-centric histories of entities, relations and temporal intervals into sequential embeddings. NADEx perturbs the query object in the forward process and reconstructs it in reverse with a Transformer denoiser conditioned on the temporal-relational context. We further derive a cosine-alignment regularizer derived from batch-wise negative prototypes, which tightens the decision boundary against implausible candidates. Comprehensive experiments on four public TKG benchmarks demonstrate that NADEx delivers state-of-the-art performance.

Temporal Knowledge Graph (TKG) extrapolation seeks to infer future facts from time-varying relational histories. Recent diffusion-based approaches improve uncertainty modeling through generative denoising, but their aggregated conditioning on subject histories may insufficiently distinguish query-specific evidence from non-salient historical facts, thereby diluting target-discriminative signals. To bridge this gap, we propose **FreqDiff**, a **Freq**uency-aware **Diff**usion framework for TKG extrapolation. Specifically, FreqDiff formulates future object prediction as query-slot denoising and develops a dual-stream denoiser that integrates temporal dependency modeling with context-aware spectral calibration. The spectral branch synthesizes history-conditioned filters from learnable bases to adaptively re-calibrate denoising representations, while a frequency-domain regularizer is proposed to align the denoised target with the gold object in spectral space. Experiments on four public TKG benchmarks demonstrate that FreqDiff achieves state-of-the-art performance.

Generative methods significantly advance event argument extraction by probabilistically generating event argument sequences in a structured format. However, existing approaches primarily rely on a single prompt to generate event arguments in a fixed, predetermined order. Such a rigid approach overlooks the complex structural and dynamic interdependencies among event arguments. In this work, we present GEMS, a multi-prompt learning framework that Generates Event arguments via Multi-perspective prompts and ontology Steering. Specifically, GEMS utilizes multiple unfilled prompts for each sentence, predicting event arguments in varying sequences to explicitly capture the interrelationships between arguments. These predictions are subsequently aggregated using a voting mechanism. Furthermore, an ontology-driven steering mechanism is proposed to ensure that the generated arguments are contextually appropriate and consistent with event-specific knowledge. Extensive experiments on two benchmark datasets demonstrate that GEMS achieves state-of-the-art performance, particularly in low-resource settings. The source code is available at: https://github.com/AONE-NLP/EAE-GEMS

Joint entity-relation extraction remains a challenging task in information retrieval, given the intrinsic difficulty in modelling the interdependence between named entity recognition (NER) and relation extraction (RE) sub-tasks. Most existing joint extraction models encode entity and relation features in a sequential or parallel manner, allowing for limited one-way interaction. However, it is not yet clear how to capture the interdependence between these two sub-tasks in a synergistic and mutually reinforcing fashion. With this in mind, we propose a novel approach for joint entity-relation extraction, named Synergetic Interaction Network (SINET) which utilizes a cross-task attention mechanism to effectively leverage contextual associations between NER and RE. Specifically, we construct two sets of distinct token representations for NER and RE sub-tasks respectively. Then, both sets of unique representation interact with one another via a cross-task attention mechanism, which exploits associated contextual information produced by concerted efforts of both NER and RE. Experiments on three benchmark datasets demonstrate that the proposed model achieves significantly better performance in joint entity-relation extraction. Moreover, extended analysis validates that the proposed mechanism can indeed leverage the semantic information produced by NER and RE sub-tasks to boost one another in a complementary way. The source code is available to the public online.

Temporal Knowledge Graph (TKG) reasoning seeks to predict future incomplete facts leveraging historical data. While existing approaches have shown effectiveness in addressing the task through various perspectives, such as graph learning and logic rules, they are limited in capturing the indeterminacy in future events, particularly in the case of rare/unseen facts. To tackle the highlighted issues, we introduce a novel approach by conceptualizing TKG reasoning as a sequence denoising process for future facts, namely DiffuTKG. Concretely, we first encodes the historical events as the conditional sequence. Then we gradually introduce Gaussian noise to corrupt target facts during the forward process and then employ a transformer-based conditional denoiser to restore them in the reverse phase. Moreover, we introduce an uncertainty regularization loss to mitigate the risk of prediction biases by favoring frequent scenarios over rare/unseen facts. Empirical results on four real-world datasets show that DiffuTKG outperforms state-of-the-art methods across multiple evaluation metrics.

Nested Named Entity Recognition (Nested NER) entails identifying and classifying entity spans within the text, including the detection of named entities that are embedded within external entities. Prior approaches primarily employ span-based techniques, utilizing the power of exhaustive searches to address the challenge of overlapping entities. Nonetheless, these methods often grapple with the absence of explicit guidance for boundary detection, resulting insensitivity in discerning minor variations within nested spans. To this end, we propose a Boundary-aware Semantic  ̲Differentiation and  ̲Filtration  ̲Network (DiFiNet) tailored for nested NER. Specifically, DiFiNet leverages a biaffine attention mechanism to generate a span representation matrix. This matrix undergoes further refinement through a self-adaptive semantic differentiation module, specifically engineered to discern semantic variances across spans. Furthermore, DiFiNet integrates a boundary filtration module, designed to mitigate the impact of non-entity noise by leveraging semantic relations among spans. Extensive experiments on three benchmark datasets demonstrate our model yields a new state-of-the-art performance.