Document-level Event Research Articles

SIAT: Document-level Event Extraction via Spatiality-Augmented Interaction Model with Adaptive Thresholding

Document-level event extraction endeavors to automatically extract structural events from a given document. Many existing approaches focus on modeling entity interactions and decoding these interactions into events, assigning each entity as an event argument. However, these approaches encounter two primary limitations: they exclusively capture semantic dependencies to model entity interactions, overlooking the indication of the spatial distribution features of entities; they decode interactions imprecisely with a hard binary-classification boundary, potentially failing to calibrate micro differences in interactions. To overcome these limitations, we introduce a novel approach termed the S patiality-augmented I nteraction Model with A daptive T hresholding (SIAT). Our method addresses the first limitation by calculating the relative position encoding of entities to represent spatial interaction features. These features are then integrated with multi-granularity semantic interactions, enhancing the modeling of entity interactions for each entity pair. Furthermore, we introduce an adaptive event decoding mechanism, which establishes a more flexible decision boundary for different entity interactions. Additionally, an adaptive loss function for threshold learning is designed to further refine the model. Experimental results demonstrate that our proposed method achieves competitive performance compared to state-of-the-art methods on two public event extraction datasets while maintaining considerable training efficiency.

AssocKD: An Association-Aware Knowledge Distillation Method for Document-Level Event Argument Extraction

Event argument extraction is a crucial subtask of event extraction, which aims at extracting arguments that correspond to argument roles when given event types. The majority of current document-level event argument extraction works focus on extracting information for only one event at a time without considering the association among events; this is known as document-level single-event extraction. However, the interrelationship among arguments can yield mutual gains in their extraction. Therefore, in this paper, we propose AssocKD, an Association-aware Knowledge Distillation Method for Document-level Event Argument Extraction, which enables the enhancement of document-level multi-event extraction with event association knowledge. Firstly, we introduce an association-aware training task to extract unknown arguments with the given privileged knowledge of relevant arguments, obtaining an association-aware model that can construct both intra-event and inter-event relationships. Secondly, we adopt multi-teacher knowledge distillation to transfer such event association knowledge from the association-aware teacher models to the event argument extraction student model. Our proposed method, AssocKD, is capable of explicitly modeling and efficiently leveraging event association to enhance the extraction of multi-event arguments at the document level. We conduct experiments on RAMS and WIKIEVENTS datasets and observe a significant improvement, thus demonstrating the effectiveness of our method.

EADRE: Event-type Aware Dynamic Representation of Entities in Document-level Event Extraction

EADRE: Event-type Aware Dynamic Representation of Entities in Document-level Event Extraction

LAAP: Learning the Argument of An Entity with Event Prompts for document-level event extraction

Document-level Event Extraction (DEE) aims to identify event types within a document and extract their corresponding arguments, which is essential for structured information provision in various NLP applications. Unlike sentence-level extraction, DEE requires handling events and arguments scattered across a document. Existing methods often focus on intricate feature interactions, neglecting explicit argument-entity relationships. We introduce a novel method, Learning the Argument of an Entity with Event Prompts (LAAP), which constructs event prompts for type detection, incorporating sentence placeholders to elicit event-specific information. Additionally, we propose an entity argument learning strategy that narrows down entity types to find the most suitable one. Experiments on the ChFinAnn and three other public datasets show that our method surpasses state-of-the-art approaches in accuracy and effectiveness.

Document-Level Event Argument Extraction with Sparse Representation Attention

Document-level Event Argument Extraction (DEAE) aims to extract structural event knowledge composed of arguments and roles beyond the sentence level. Existing methods mainly focus on designing prompts and using Abstract Meaning Representation (AMR) graph structure as additional features to enrich event argument representation. However, two challenges still remain: (1) the long-range dependency between event trigger and event arguments and (2) the distracting context in the document towards an event that can mislead the argument classification. To address these issues, we propose a novel document-level event argument extraction model named AMR Parser and Sparse Representation (APSR). Specifically, APSR sets inter- and intra-sentential encoders to capture the contextual information in different scopes. Especially, in the intra-sentential encoder, APSR designs three types of sparse event argument attention mechanisms to extract the long-range dependency. Then, APSR constructs AMR semantic graphs, which capture the interactions among concepts well. Finally, APSR fuses the inter- and intra-sentential representations and predicts what role a candidate span plays. Experimental results on the RAMS and WikiEvents datasets demonstrate that APSR achieves a superior performance compared with competitive baselines in terms of F1 by 1.27% and 3.12%, respectively.

EIGP: document-level event argument extraction with information enhancement generated based on prompts

EIGP: document-level event argument extraction with information enhancement generated based on prompts

Recurrent event query decoder for document-level event extraction

Document-level event extraction is a challenging task in natural language processing, as it involves multiple events within a document and scattered event arguments across sentences. To tackle these challenges, we propose a recurrent event query decoder, i.e., a recurrent module that dynamically updates event queries to capture cross-event dependencies. Our approach then generates arguments by extracting role-argument relations using bilinear mapping, which helps address the issue of scattered arguments. Experimental results demonstrate that our proposed approach outperforms state-of-the-art models on a large-scale public dataset and actual application data, achieving significant improvements in F1-score. In domain-specific event extraction applications, our method achieves higher accuracy with fewer resources compared to general-purpose large language models.

Towards document-level event extraction via Binary Contrastive Generation

In this study, we explored the complexities of document-level event extraction, a process that involves identifying multiple events and their associated arguments within a document. The primary challenges include (1) the distribution of event arguments across numerous sentences, resulting in long-distance dependencies, and (2) the complex relationships between multiple events due to the overlapping and dispersion of event arguments throughout the document. To address these issues, we propose the Binary Contrastive Generation (BCG) method. BCG utilizes binary auto-regressive generation in both the original and reversed sequences to learn binary-directed interdependency, thereby capturing the long-distance dependency of dispersed event arguments. To handle intricate multi-event relationships, BCG enhances the global semantic representation of multiple events by extraction-oriented contrastive learning. Specifically, event representations derived from identical event arguments in varying sequences are deemed positive pairs, while those from different event arguments in the same sequence are classified as negative pairs. Experimental results on three public datasets demonstrate that BCG outperforms existing methods, achieving an increase of 2.6 in absolute F1 score. Further analysis revealed that BCG effectively models the dependency of dispersed event arguments and enhances the semantic representation of multiple events.

TGIN: Document-level event extraction with two-phase graph inference network

Document-level event extraction aims to extract event records from a whole document that contain numerous entities scattered across multiple sentences. Efficiently modeling the interactions among these entities is crucial. However, previous methods suffer from two main shortcomings. Firstly, they tend to implicitly model key information, which can result in representations with higher levels of noise. Secondly, they excessively consider irrelevant entities, thereby reducing extraction efficiency and precision. To address these issues, we propose a novel Two-phase Graph Inference Network (TGIN) approach for extracting document-level events. In the first phase, TGIN constructs a heterogeneous document-level graph to capture complex interactions among nodes of different granularity, enabling the acquisition of document-aware features. Subsequently, a dedicated module is developed to extract relevant entity pairs within the same event record. This module utilizes a key information aggregator with an attention mechanism to explicitly aggregate key sentences for entity pairs. In the second phase, the entity links predicted in the first phase serve as prior information to construct the entity-level graph, which focuses on modeling interactions between entity pairs that potentially share the same event link, effectively reducing error propagation. Experimental results on the publicly available document-level event extraction dataset ChFinAnn demonstrate the superiority of our framework over most existing models.

Token-Event-Role Structure-Based Multi-Channel Document-Level Event Extraction

Document-level event extraction is a long-standing challenging information retrieval problem involving a sequence of sub-tasks: entity extraction, event type judgment, and event type-specific multi-event extraction. However, addressing the problem as multiple learning tasks leads to increased model complexity. Also, existing methods insufficiently utilize the correlation of entities crossing different events, resulting in limited event extraction performance. This article introduces a novel framework for document-level event extraction, incorporating a new data structure called token-event-role and a multi-channel argument role prediction module. The proposed data structure enables our model to uncover the primary role of tokens in multiple events, facilitating a more comprehensive understanding of event relationships. By leveraging the multi-channel prediction module, we transform entity and multi-event extraction into a single task of predicting token–event pairs, thereby reducing the overall parameter size and enhancing model efficiency. The results demonstrate that our approach outperforms the state-of-the-art method by 9.5 percentage points in terms of the F 1 score, highlighting its superior performance in event extraction. Furthermore, an ablation study confirms the significant value of the proposed data structure in improving event extraction tasks, further validating its importance in enhancing the overall performance of the framework.

Global information enhancement and subgraph-level weakly contrastive learning for lightweight weakly supervised document-level event extraction

Document-level event extraction (DEE) is a branch of information extraction task that is valuable but difficult at present. To effectively implement DEE, previous works with better performance are often accompanied by larger parameters and computation. In this paper, we propose a novel framework based on global information enhancement and subgraph-level weakly contrastive learning, which bring better performance at lower extra computing costs. We verify the effectiveness of our method in a lightweight DEE model. The experimental results indicate that our proposed method outperforms other approaches in terms of the F1 score for both overall event extraction evaluation and single event extraction. In the inference phase, our model uses only 25% of the GPU memory required by the optimal model and maintains the advantage of 6.4 times faster inference speed.

EACE: A document-level event argument extraction model with argument constraint enhancement

There are two key challenges remaining for the document-level event argument extraction tasks: long-range dependency and same-role argument assignment. The existing methods could not effectively handle the above two challenges at the same time, resulting in argument misidentification and over- or under-extraction, reducing the precision and recall of event argument extraction. In this paper, we propose a document-level event argument extraction model with argument constraint enhancement (EACE), which constructs the argument constraint tree using the hierarchical constraints between arguments to address the above two challenges simultaneously. Specifically, EACE first constructs an argument constraint decoder and uses abstractive summarization to establish the long-range hierarchical constraint relationships between arguments and to obtain the trunk structure of the argument constraint tree, which improves argument identification precision. Secondly, EACE calculates dynamic branch thresholds to expand the branch structure of the argument constraint tree and improve the recall of argument extraction. Extensive experiments on WIKIEVENTS and RAMS have shown that EACE outperforms the baseline models by 2.2% F1 and 0.2% F1, respectively. Moreover, it exceeds the baseline model (PAIE) by up to 17.1% F1 in the same-role argument assignment setting in WIKIEVENTS.

Modeling Graph Neural Networks and Dynamic Role Sorting for Argument Extraction in Documents

The existing methods for document-level event extraction mainly face two challenges. The first challenge is effectively capturing event information that spans across sentences. The second challenge is using predefined orders to extract event arguments while disregarding the dynamic adjusting of the order according to the importance of argument roles. To address these issues, we propose a model based on graph neural networks which realizes the semantic interaction among documents, sentences, and entities. Additionally, our model adopts a dynamic argument detection strategy, extracting arguments depending on their number in correspondence with each role. The experimental results confirm the outperformance of our model, which surpasses previous methods by 7% and 1.9% in terms of an F1 score.

Improving document-level event detection with event relation graph

The correlation between events within the same document plays a crucial role in event detection. Most existing detection models often ignore event correlations, which is not applicable to multi-event detection at the document level. In the real world, it is a common phenomenon that the probability of correlated events occurring simultaneously is much greater than the probability of uncorrelated events occurring simultaneously. Based on this observation, we propose an event correlation-based document-level event detection model (EventCo-ED) to capture the document-level association between events. Specifically, EventCo-ED first constructs a novel event relation graph (ERG) to capture the correlation between events and uses this correlation to extract the topic features of a document. Secondly, DMBERT is employed to get sentence-level contextual representation as the local features. Finally, a gated feature fusion module is used to aggregate topic features and local features, and a correlation suppression module is used to increase the probability that related events are detected simultaneously and suppress the probability that unrelated events are detected simultaneously. Experimental results show that the proposed model can simultaneously improve the precision and recall of multi-event detection and achieve 1.56% and 3.63% F1 improvements on the LEVEN and MAVEN corpuses, respectively.

Chinese Document-Level Emergency Event Extraction Dataset and Corresponding Methods

Structured extraction of emergency event information can effectively enhance the ability to respond to emergency events. This article focuses on extracting Chinese document-level emergency events, which entails addressing two key issues in this field: related datasets and the problem of role overlapping between candidate entities, which has been overlooked in existing DEE (document-level event extraction) studies that predominantly employed sequence annotation for candidate entity extraction. To tackle these challenges, we constructed a Chinese document-level emergency extraction dataset (CDEEE) and provides annotations for argument scattering, multiple events, and role overlapping. Additionally, a model named RODEE is proposed to address the role overlapping problem in DEE tasks. RODEE employs two independent modules to represent the head and tail positions of candidate entities, and utilizes a multiplication attention mechanism to interact between the two, generating a scoring matrix. Subsequently, role-overlapping candidate entities are predicted to facilitate the completion of DEE tasks. Experiments were conducted on our manually annotated dataset, CDEEE, and the results show that RODEE effectively solves the problem of role overlapping among candidate entities, resulting in improved performance of the DEE model, with an F1 value of 77.7%.

Document-level Event Extraction - A Survey of Methods and Applications

Event extraction aims to detect occurrences of specified types and extract corresponding event arguments from unstructured data input, which is an integral part of information extraction [1]. Many downstream tasks, such as text summarization, causal relationship identification, and event reasoning, make extensive use of event extraction. However, most of the existing research on event extraction remains at the sentence level. Document-level event extraction is still under exploration and lacks relevant review. Focusing on the task of document-level event extraction, this survey first divides the existing technologies into three categories and introduces the most representative models; Then, we list some commonly used datasets for document-level event extraction with their usage messages; Finally, we analyse the current research gaps of document-level event extraction and future research trends.

Role Knowledge Prompting for Document-Level Event Argument Extraction

Document-level event argument extraction (DEAE) aims to identify the arguments corresponding to the roles of a given event type in a document. However, arguments scattering and arguments and roles overlapping make DEAE face great challenges. In this paper, we propose a novel DEAE model called Role Knowledge Prompting for Document-Level Event Argument Extraction (RKDE), which enhances the interaction between templates and roles through a role knowledge guidance mechanism to precisely prompt pretrained language models (PLMs) for argument extraction. Specifically, it not only facilitates PLMs to understand deep semantics but also generates all the arguments simultaneously. The experimental results show that our model achieved decent performance on two public DEAE datasets, with 3.2% and 1.4% F1 improvement on Arg-C, and to some extent, it addressed the overlapping arguments and roles.

DEEDP: Document-Level Event Extraction Model Incorporating Dependency Paths

Document-level event extraction (DEE) aims at extracting event records from given documents. Existing DEE methods handle troublesome challenges by using multiple encoders and casting the task into a multi-step paradigm. However, most of the previous approaches ignore a missing feature by using mean pooling or max pooling operations in different encoding stages and have not explicitly modeled the interdependency features between input tokens, and thus the long-distance problem cannot be solved effectively. In this study, we propose Document-level Event Extraction Model Incorporating Dependency Paths (DEEDP), which introduces a novel multi-granularity encoder framework to tackle the aforementioned problems. Specifically, we first designed a Transformer-based encoder, Transformer-M, by adding a Syntactic Feature Attention mechanism to the Transformer, which can capture more interdependency information between input tokens and help enhance the semantics for sentence-level representations of entities. We then stacked Transformer-M and Transformer to integrate sentence-level and document-level features; we thus obtained semantic enhanced document-aware representations for each entity and model long-distance dependencies between arguments. Experimental results on the benchmarks MUC-4 and ChFinAnn demonstrate that DEEDP achieves superior performance over the baselines, proving the effectiveness of our proposed methods.

Document-Level Event Role Filler Extraction Using Key-Value Memory Network

Previous work has demonstrated that end-to-end neural sequence models work well for document-level event role filler extraction. However, the end-to-end neural network model suffers from the problem of not being able to utilize global information, resulting in incomplete extraction of document-level event arguments. This is because the inputs to BiLSTM are all single-word vectors with no input of contextual information. This phenomenon is particularly pronounced at the document level. To address this problem, we propose key-value memory networks to enhance document-level contextual information, and the overall model is represented at two levels: the sentence-level and document-level. At the sentence-level, we use BiLSTM to obtain key sentence information. At the document-level, we use a key-value memory network to enhance document-level representations by recording information about those words in articles that are sensitive to contextual similarity. We fuse two levels of contextual information by means of a fusion formula. We perform various experimental validations on the MUC-4 dataset, and the results show that the model using key-value memory networks works better than the other models.

Exploiting event-aware and role-aware with tree pruning for document-level event extraction

Exploiting event-aware and role-aware with tree pruning for document-level event extraction