Search

The conventional approach to event extraction requires predefined event types and their corresponding annotations to train event extractors. However, these prerequisites are often difficult to satisfy in real-world applications. To automatically induct event types, most work has been devoted to clustering event triggers, where a cluster of event triggers is represented as an event type. Some works use trigger semantics, while others use co-occurrence relationships to cluster triggers. However, the clustering results of event triggers obtained by the above work are not sufficiently detailed in describing event types, making it difficult to accurately determine the corresponding event types manually. This paper proposes an open-domain event type induction framework that automatically discovers a set of event types from a given corpus. Unlike previous work on event trigger clustering, this paper takes into consideration the hierarchical relationship of event types to partition the event trigger clusters into event mains and subtypes. The framework employs a latent variable-based neural generation module and a semantic-based clustering module, the former of which obtains event trigger clusters representing the main types of events by jointly projecting the co-occurrence and semantic information of event triggers into a latent space for event type latent variable mining, and the latter of which further divides these event trigger clusters into event subtypes based on semantic information. Finally, experiment results show that, compared with the benchmark model, the ETGen-Clus can improve event type quality scores of 6.23% and 3.11% on the two datasets, respectively. [ABSTRACT FROM AUTHOR]

News event monitoring systems allow real-time monitoring of a large number of events reported in the news, including the urgent and critical events comprising the so-called hard news. These systems heavily rely on natural language processing (NLP) to perform automatic event extraction at scale. While state-of-the-art event extraction models are readily available, integrating them into a news event monitoring system is not as straightforward as it seems due to practical issues related to model selection, robustness, and scale. To address this gap, we present a study on the practical use of event extraction models for news event monitoring. Our study focuses on the key task of closed-domain main event extraction (CDMEE), which aims to determine the type of the story's main event and extract its arguments from the text. We evaluate a range of state-of-the-art NLP models for this task, including those based on pre-trained language models. Aiming at a more realistic evaluation than done in the literature, we introduce a new dataset manually labeled with event types and their arguments. Additionally, we assess the scalability of CDMEE models and analyze the trade-off between accuracy and inference speed. Our results give insights into the performance of state-of-the-art NLP models on the CDMEE task and provide recommendations for developing effective, robust, and scalable news event monitoring systems. [ABSTRACT FROM AUTHOR]

In response to the challenges of accurately identifying event triggers and elements in long texts related to aquaculture, existing models struggle to differentiate between elements and triggers, as well as effectively recognize complete entity texts. To tackle this issue, this study proposes an algorithm for extracting fish disease events based on pseudo triggers and augmented event element data. The method starts by constructing pseudo samples using the original dataset. Two types of noise datasets are then generated: a trigger noise dataset constructed based on fish disease triggers and an entity noise dataset with varying levels of entity noise constructed based on fish disease entities. Next, three parallel neural networks are deployed to extract sample features from these datasets. The fish disease event extraction for the source dataset employs multi-label classification. For the trigger noise dataset, the sample features are activated using the sigmoid function, and the MRSE loss is utilized for optimization of this branch. For the entity noise dataset, the sample features are activated using the Relu function, and the XOR loss is used for optimization. Finally, the losses from the three branches are combined with weighted summation to obtain the fusion loss. The experimental results on the fish disease dataset used in this paper show that the proposed algorithm achieves an average accuracy of 78.71%, 78.95%, and 79.43% on F1, recall, and precision, respectively, which is a maximum improvement of 11.201%, 11.849%, and 12.421% in accuracy with respect to the baseline model on F1, recall, and precision, respectively. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Event extraction aims to extract human-interest information from massive amounts of unstructured text. Currently, most existing event extraction methods are based on general corpora and rarely consider domain- specific prior knowledge. Moreover, most methods cannot handle well the case where multiple events exist in the same document, and they perform poorly when faced with a large number of negative examples. To address these issues, this paper proposes a model called Fin-PTPCG based on Fin-BERT (financial bidirectional encoder representation from Transformers) and PTPCG (pseudo-trigger-aware pruned complete graph). This method fully utilizes the expression ability of the Fin-BERT pre- training model and incorporates domain- specific prior knowledge during the encoding stage. In the event detection module, multiple binary classifiers are stacked to ensure that the model can effectively identify the situation of multiple events in a document and screen out negative examples. Combined with the decoding module of the PTPCG model, entities are extracted and connected into a complete graph and pruned by calculating a similarity matrix. The problem of unlabeled triggers is solved by selecting pseudo-triggers. Finally, the event extraction is achieved by the event classifier. This method achieves a 0.7 and 3.7 percentage points improvement in F1 score compared to the baselines on the ChFinAnn and Duee-fin datasets for the event extraction task. [ABSTRACT FROM AUTHOR]

The success of a nanopore experiment relies not only on the quality of the experimental design but also on the performance of the analysis program utilized to decipher the ionic perturbations necessary for understanding the fundamental molecular intricacies. An event extraction framework is developed that leverages parallel computing, efficient memory management, and vectorization, yielding significant performance enhancement. The newly developed abf‐ultra‐simple function extracts key parameters from the header critical for the operation of open‐seek‐read‐close data loading architecture running on multiple cores. This underpins the swift analysis of large files where an ≈ × 18 improvement is found for a 100 min‐long file (≈4.5 GB) compared to the more traditional single (cell) array data loading method. The application is benchmarked against five other analysis platforms showcasing significant performance enhancement (>2 ×–1120 ×). The integrated provisions for batch analysis enable concurrently analyzing multiple files (vital for high‐bandwidth experiments). Furthermore, the application is equipped with multi‐level data fitting based on abrupt changes in the event waveform. The application condenses the extracted events to a single binary file improving data portability (e.g., 16 GB file with 28 182 events reduces to 47.9 MB–343 × size reduction) and enables a multitude of post‐analysis extractions to be done efficiently. [ABSTRACT FROM AUTHOR]

In the formal procedure of Chinese civil cases, the textual materials provided by different parties describe the development process of the cases. It is a difficult but necessary task to extract the key information for the cases from these textual materials and to clarify the dispute focus of related parties. Currently, officers read the materials manually and use methods, such as keyword searching and regular matching, to get the target information. These approaches are time‐consuming and heavily depend on prior knowledge and the carefulness of the officers. To assist the officers in enhancing working efficiency and accuracy, we conduct a case study of detecting disputes from Chinese divorce cases based on proposing a Two‐Round‐Labeling (TRL) event extracting technique in this article. We implement the Judicial Intelligent Assistant (JIA) system according to the proposed approach to (1) automatically extract focus events from divorce case materials, (2) align events by identifying co‐reference among them, and (3) detect conflicts among events brought by the plaintiff and the defendant. With the JIA system, it is convenient for judges to determine the disputed issues in Chinese divorce cases. Experimental results demonstrate that the proposed approach and system can obtain the focus of Chinese divorce cases and detect conflicts more effectively and efficiently compared with the existing method. [ABSTRACT FROM AUTHOR]

The timely extraction of event information from enormous amounts of textual data is a critical research problem. Event extraction using deep learning technology has gained academic attention as a result of the fast growth of deep learning. Event extraction requires costly, expert-level, high-quality human annotations. As a result, developing a data-efficient event extraction model that can be trained using only a few labelled samples has emerged as a key difficulty. Existing research work focuses mainly on the structured data with supervised models. The proposed work focuses on Movie Scene Event Extraction, a practical media analysis problem that seeks to extract structured events from unstructured movie screenplays. We suggest using the correlation between various argument roles in situations where different argument roles in a movie scene share similar qualities. This can be beneficial to the Movie Scene Argument Extraction (argument classification and identification) and film scene trigger extraction (Trigger recognition and classifying). In order to represent the relation between different roles in argument and their respective roles, we propose a Superior Concept of Role (SRC) as a top-level idea of a role that is based on the classic argument role, as well as an SRC-based Graph Attention System (GAT). To assess the efficacy of the model we designed, we constructed the dataset MovieSceneEvent to extract movies' scene-related events. Additionally, we conducted tests on an existing dataset in order to compare results with different models. Results from the experiments like extraction of words, aspect keywords from the documents indicate that our model does better than other models. Furthermore, the information on the relationship between the argument roles helps improve the effectiveness of film scene extraction of events. [ABSTRACT FROM AUTHOR]

For the large number of news reports generated every day, in order to obtain effective information from these unstructured news text data more efficiently. In this paper, we study the real-time crawling of news data from news websites through crawling techniques and propose a BERT model-based approach to extract events from news long text. In this study, NetEase news website is selected as an example for realtime extraction to crawl the news data of this website. BERT model as a pre-trained model based on two-way encoded representation of transformer performs well on natural language understanding and natural language generation tasks. In this study, we will fine-tune the training based on BERT model on news corpus related dataset and perform sequence annotation through CRF layer to finally complete the event extraction task. In this paper, the DUEE dataset is chosen to train the model, and the experiments show that the overall performance of the BERT model is better than other network models. Finally, the model of this paper is further optimised, using the ALBERT and RoBERTa models improved on the basis of the BERT model, experiments were conducted, the results show that both models are improved compared to the BERT model, the ALBERT model algorithm performs the best, the model algorithm's F1 value is 1% higher than that of BERT. The results show that the performance is optimised. [ABSTRACT FROM AUTHOR]

News event monitoring systems allow real-time monitoring of a large number of events reported in the news, including the urgent and critical events comprising the so-called hard news. These systems heavily rely on natural language processing (NLP) to perform automatic event extraction at scale. While state-of-the-art event extraction models are readily available, integrating them into a news event monitoring system is not as straightforward as it seems due to practical issues related to model selection, robustness, and scale. To address this gap, we present a study on the practical use of event extraction models for news event monitoring. Our study focuses on the key task of closed-domain main event extraction (CDMEE), which aims to determine the type of the story’s main event and extract its arguments from the text. We evaluate a range of state-of-the-art NLP models for this task, including those based on pre-trained language models. Aiming at a more realistic evaluation than done in the literature, we introduce a new dataset manually labeled with event types and their arguments. Additionally, we assess the scalability of CDMEE models and analyze the trade-off between accuracy and inference speed. Our results give insights into the performance of state-of-the-art NLP models on the CDMEE task and provide recommendations for developing effective, robust, and scalable news event monitoring systems.

Event extraction (EE) generally contains two subtasks: viz., event detection and argument extraction. Owing to the success of machine reading comprehension (MRC), some researchers formulate EE into MRC frameworks. However, existing MRC-based EE techniques are pipeline methods that suffer from error propagation. Moreover, the correlation between event types and argument roles is pre-defined by experts, which is time-consuming and inflexible. To avoid these issues, event detection and argument extraction are formalized as joint MRC. Different from previous methods, which just generate questions for argument roles for identified event types, questions are generated for all arguments that appear in the given sentence in our approach. Moreover, an end-to-end MRC model, JEEMRC, is proposed, which consists of an event classifier and a machine reader with a coarse-to-fine attention mechanism. Our proposed model can train two subtasks jointly to alleviate error propagation and utilizes interaction information between event types and argument roles to improve the performance of both tasks. Experiments on ACE 2005 verify that our JEEMRC achieves competitive results compared with previous work. In addition, it performs well when detecting events and extracting arguments in data-scarce scenarios. [ABSTRACT FROM AUTHOR]

Event extraction (EE) is an important natural language processing task. With the passage of time, many powerful and effective models for event extraction tasks have been developed. However, there has been limited research on complex overlapping event extraction. Therefore, we propose a new cascade decoding model: A Joint Learning Framework for Cascade Decoding with Multi-Feature Fusion and Conditional Enhancement for Overlapping Event Extraction. 1) In this model, we introduce a cascade decoding mechanism with multi-feature fusion to better capture the interaction between decoding layers. 2) Additionally, we introduce an enhanced conditional layer normalization (ECLN) mechanism to enhance the interaction between subtasks. Simultaneously, the use of a cascade decoding model effectively addresses the problem of overlapping events. The model successively performs three subtasks, type detection, trigger word extraction and argument extraction. All three subtasks learned together in a framework, and a new conditional normalization mechanism is used to capture dependencies among these subtasks. The experiments are conducted using the overlapping event benchmark, FewFC dataset. The experimental evaluation demonstrates that our model achieves a higher F1 score on the overlapping event extraction task compared to the original overlapping event extraction model. [ABSTRACT FROM AUTHOR]

Social media platforms have emerged as fertile ground for the proliferation of hate speech, which can exacerbate the dissemination of hate crimes. The Federal Bureau of Investigation UCR Program gathers data on hate crimes and disseminates annual reports to identify national patterns and inform law enforcement agencies and policymakers, these reports often fail to keep pace with urgent demands. Real-time monitoring and predictive analysis of hate crime trends are imperative for more effective prevention and response efforts. This paper presents a framework that leverages information extraction techniques to extract incidents from articles published in The New York Times, enabling accurate prediction of hate crime trends at both the federal and state levels. Experimental findings demonstrate the superiority of our approach compared to other traditional methods. By expanding forecasting approaches for federal and state levels' hate crime trends, this framework offers valuable insights for law enforcement agencies and policymakers. [ABSTRACT FROM AUTHOR]

Historical news media reports serve as a vital data source for understanding the risk of urban ground collapse (UGC) events. At present, the application of large language models (LLMs) offers unprecedented opportunities to effectively extract UGC events and their spatiotemporal information from a vast amount of news reports and media data. Therefore, this study proposes an LLM-based inventory construction framework consisting of three steps: news reports crawling, UGC event recognition, and event attribute extraction. Focusing on Zhejiang province, China, as the test region, a total of 27 cases of collapse events from 637 news reports were collected for 11 prefecture-level cities. The method achieved a recall rate of over 60% and a precision below 35%, indicating its potential for effectively and automatically screening collapse events; however, the accuracy needs to be improved to account for confusion with other urban collapse events, such as bridge collapses. The obtained UGC event inventory is the first open access inventory based on internet news reports, event dates and locations, and collapse co-ordinates derived from unstructured contents. Furthermore, this study provides insights into the spatial pattern of UGC frequency in Zhejiang province, effectively supplementing the statistical data provided by the local government. [ABSTRACT FROM AUTHOR]

As internet information expands rapidly, extracting valuable event information from unstructured text has become an important research topic. This paper proposes an improved GPT2 model, termed HACLV-GPT2, which is the initial utilization of a GPT-like architecture for the purpose of event extraction. The model utilizes a generative input template and incorporates a hybrid attention mechanism to enhance the understanding of complex contexts. Additionally, the HACLV-GPT2 model employs a layer-vector fusion strategy to optimize the output of Transformer Blocks, effectively boosting prediction performance. The experimental results show that the HACLV-GPT2 model performs excellently in both event argument extraction and event type detection tasks, with F1 values of 0.8020 and 0.9614, respectively, surpassing several baseline models. This outcome fully validates the effectiveness and superiority of the proposed method. Furthermore, ablation experiments confirm the critical role of the hybrid attention mechanism and layer-vector fusion strategy in performance improvement.

As an important task in the field of information extraction, event detection is widely used in event graph construction and network public opinion monitoring. Although the existing methods (such as BGCN, MGRN-EE, etc.) have obtained well performance on event detection by utilizing various features from text, they neglect that the events in data follows a long-tailed distribution, which leads to a serious bias in the trained event detection model. By following a simple but effective way to address this issue, we propose an event detection model based on event sentence pre-determination, termed as ES4ED. The model first employs classification method to identify the sentences that contain events semantically (called event sentences), and then conducts event detection on these event sentences to solve the long-tailed distribution of events. ES4ED consists of three components: the semantic encoder, the event sentence decider and the event detector. First, the semantic encoder encodes the words semantically. Then, the event sentence decider identifies event sentences by classification. Finally, the event sentences are input to the event detector to complete the event triggers identification and classification. Experimental results on the public dataset ACE2005 show that the F1 score of the proposed model achieves 79.2% and 76.5% on trigger identification and trigger classification, respectively, which are significantly improved compared with the existing typical works.

Document-level event extraction aims to extract event-related information from an unstructured document composed of multiple sentences. Existing approaches are not effective due to the challenge of event arguments that are scattered across multi-sentences and they pay more attention to the coreference relationship between entity mentions. However, it is an extremely common phenomenon that there are a large number of crossing sentences pronouns that referring to entity mentions. These pronouns also contain rich semantic information related to events in the document. Therefore, there is still a challenge that how to effectively construct the mention–pronoun coreference relationship and better learn the rich semantic entities representations for DEE. Aiming at the above problems, we propose a novel document-level multi-task learning approach based on coreference-aware dynamic heterogeneous graph network for event extraction, named DMCGEE. Specifically, first, an information enhancement extractor module is constructed to effectively capture multi-types of semantic association information for mentions representations. Second, a mention–pronoun coreference resolution method is proposed to capture mention–pronoun coreference resolution pairs, and a coreference-aware dynamic heterogeneous graph network is constructed to help sentences and mentions representations to focus on the effective global related information, thereby improving the performance of DMCGEE. Experiments show that DMCGEE outperforms the state-of-the-art. [ABSTRACT FROM AUTHOR]

Textual documents serve as representations of discussions on a variety of subjects. These discussions can vary in length and may encompass a range of events or factual information. Present trends in constructing knowledge bases primarily emphasize fact-based common sense reasoning, often overlooking the temporal dimension of events. Given the widespread presence of time-related information, addressing this temporal aspect could potentially enhance the quality of common-sense reasoning within existing knowledge graphs. In this comprehensive survey, we aim to identify and evaluate the key tasks involved in constructing temporal knowledge graphs centered around events. These tasks can be categorized into three main components: (a) event extraction, (b) the extraction of temporal relationships and attributes, and (c) the creation of event-based knowledge graphs and timelines. Our systematic review focuses on the examination of available datasets and language technologies for addressing these tasks. An in-depth comparison of various approaches reveals that the most promising results are achieved by employing state-of-the-art models leveraging large pre-trained language models. Despite the existence of multiple datasets, a noticeable gap exists in the availability of annotated data that could facilitate the development of comprehensive end-to-end models. Drawing insights from our findings, we engage in a discussion and propose four future directions for research in this domain. These directions encompass (a) the integration of pre-existing knowledge, (b) the development of end-to-end systems for constructing event-centric knowledge graphs, (c) the enhancement of knowledge graphs with event-centric information, and (d) the prediction of absolute temporal attributes. [ABSTRACT FROM AUTHOR]

Copyright of Electric Power is the property of Electric Power Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Event extraction, grounded in semantic relationships, can serve as a simplified relation extraction. In this study, we propose an efficient open-domain event annotation framework tailored for subsequent information extraction, with a specific focus on its applicability to low-resource languages. The proposed event annotation method, which is based on event semantic elements, demonstrates substantial time-efficiency gains over traditional Universal Dependencies (UD) tagging. We show how language-specific pretraining outperforms multilingual counterparts in entity and relation extraction tasks and emphasize the importance of task- and language-specific fine-tuning for optimal model performance. Furthermore, we demonstrate the improvement of model performance upon integrating UD information during pre-training, achieving the F1 score of 71.16 and 60.43% for entity and relation extraction respectively. In addition, we showcase the usage of our extracted event graph for improving node classification in a retail banking domain. This work provides valuable guidance on improving information extraction and outlines a methodology for developing training datasets, particularly for low-resource languages.