Search

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.

These days, a lot of crime-related events take place all over the world. Most of them are reported in news portals and social media. Crime-related event extraction from the published texts can allow monitoring, analysis, and comparison of police or criminal activities in different countries or regions. Existing approaches to event extraction mainly suggest processing texts in English, French, Chinese, and some other resource-rich and well-annotated languages. This paper presents a parallel corpus-based approach that follows a closed-domain event extraction methodology to event extraction from web news articles in low-resource languages. To identify the event, its arguments, and the arguments’ roles in the source-language part of the corpus we utilize an enhanced pattern-based method that involves the multilingual synonyms dictionary with knowledge about crime-related concepts and logic-linguistic equations. The event extraction from the target-language part of the corpus uses a cross-lingual crime-related event extraction transfer technique that is based on supplementary knowledge about the semantic similarity patterns of the considered pair of languages. The presented approach does not require a preliminarily annotated corpus for training making it more attractive to low-resource languages and allows extracting TRANSFER, CRIME, and POLICE types of events and their seven subtypes from various topics of news articles simultaneously. Implementation of our approach for the Russian-Kazakh parallel corpus of news portals articles allowed obtaining the F1-measure of crime-related event extraction of over 82% for the source language and 63% for the target language.

Information extraction (IE) is a challenging task, particularly when dealing with highly heterogeneous data. State-of-the-art data mining technologies struggle to process information from textual data. Therefore, various IE techniques have been developed to enable the use of IE for textual data. However, each technique differs from one another because it is designed for different data types and has different target information to be extracted. This study investigated and described the most contemporary methods for extracting information from textual data, emphasizing their benefits and shortcomings. To provide a holistic view of the domain, this comprehensive systematic literature review employed a systematic mapping process to summarize studies published in the last six years (from 2017 to 2022). It covers fundamental concepts, recent approaches, applications, and trends, in addition to challenges and future research prospects in this domain area. Based on an analysis of 161 selected studies, we found that the state-of-the-art models employ deep learning to extract information from textual data. Finally, this study aimed to guide novice and experienced researchers in future research and serve as a foundation for this research area.

Linking event triggers with their respective arguments is an essential component for building an event extraction system. It is challenging to link event triggers with their corresponding argument triggers when the sentence contains multiple event and argument triggers. The task becomes even more challenging in a low-resource setup due to the unavailability of natural language processing resources and tools. In this paper, we study the event-argument linking task based on disaster event ontology in a low resource setup. We use BERT and non-BERT-based deep learning models in both monolingual and cross-lingual event-argument linking tasks. We also perform an ablation study of various features like position embeddings (PE), position indicator (PI), and segment ID (SI) to understand their contribution to performance improvement in non-BERT-based models. Using three different languages viz. Hindi, Bengali, and Marathi, we compare the results with multilingual BERT-based deep neural models in both monolingual and cross-lingual scenarios. We observe that the multilingual BERT-based model outperforms the best performing non-BERT-based model in cross-lingual settings. But in monolingual settings, the performance is similar in Hindi and Bengali datasets and slightly better in Marathi dataset. We choose the disaster domain due to its social implications. Our current experiments can be helpful in mining important information related to disaster events from news articles and building event knowledge graphs in low-resource languages.

Research on crude oil price forecasting has attracted tremendous attention from scholars and policymakers due to its significant effect on the global economy. Besides supply and demand, crude oil prices are largely influenced by various factors, such as economic development, financial markets, conflicts, wars, and political events. Most previous research treats crude oil price forecasting as a time series or econometric variable prediction problem. Although recently there have been researches considering the effects of real-time news events, most of these works mainly use raw news headlines or topic models to extract text features without profoundly exploring the event information. In this study, a novel crude oil price forecasting framework, AGESL, is proposed to deal with this problem. In our approach, an open domain event extraction algorithm is utilized to extract underlying related events, and a text sentiment analysis algorithm is used to extract sentiment from massive news. Then a deep neural network integrating the news event features, sentimental features, and historical price features is built to predict future crude oil prices. Empirical experiments are performed on West Texas Intermediate (WTI) crude oil price data, and the results show that our approach obtains superior performance compared with several benchmark methods.

Motivation: The scientific literature embeds an enormous amount of relational knowledge, encompassing interactions between biomedical entities, like proteins, drugs, and symptoms. To cope with the ever-increasing number of publications, researchers are experiencing a surge of interest in extracting valuable, structured, concise, and unambiguous information from plain texts. With the development of deep learning, the granularity of information extraction is evolving from entities and pairwise relations to events. Events can model complex interactions involving multiple participants having a specific semantic role, also handling nested and overlapping definitions. After being studied for years, automatic event extraction is on the road to significantly impact biology in a wide range of applications, from knowledge base enrichment to the formulation of new research hypotheses. Results: This paper provides a comprehensive and up-to-date survey on the link between event extraction and natural language understanding, focusing on the biomedical domain. First, we establish a flexible event definition, summarizing the terminological efforts conducted in various areas. Second, we present the event extraction task, the related challenges, and the available annotated corpora. Third, we deeply explore the most representative methods and present an analysis of the current state-of-the-art, accompanied by performance discussion. To help researchers navigate the avalanche of event extraction works, we provide a detailed taxonomy for classifying the contributions proposed by the community. Fourth, we compare solutions applied in biomedicine with those evaluated in other domains, identifying research opportunities and providing insights for strategies not yet explored. Finally, we discuss applications and our envisions about future perspectives, moving the needle on explainability and knowledge injection.

Event argument extraction, which aims to identify arguments of specific events and label their roles, is a challenging subtask of event extraction. Previous approaches solve this problem in a two-stage manner that first extracts named entities as argument candidates and then determines their roles. However, many nested entities may be missed or wrongly predicted during the argument candidate extraction procedure, which substantially affects the performance of the downstream classifier. In this paper, we propose a novel one-step question answering based framework, which performs argument candidate extraction and argument role classification simultaneously to mitigate the error propagation problem in conventional two-stage methods. Since the conventional question answering based framework cannot be applied directly to this task, we design a Question Answering based Sequence Labeling (QA-SL) model to tackle inexistent argument roles and multiple argument token spans. Moreover, considering the overwhelming number of parameters in question answering based neural network models and the relatively small size of event extraction corpus, we fine-tune the pre-trained model from BERT to mitigate the data scarcity problem. Extensive experiments demonstrate the benefits of the proposed method, leading to a competitive performance compared with state-of-the-art methods. To the best of our knowledge, this is the first work to cast event argument extraction as a question answering task.

Event Extraction plays an important role in information-extraction to understand the world. Event extraction could be split into two subtasks: one is event trigger extraction, the other is event arguments extraction. However, the F1-Score of event arguments extraction is much lower than that of event trigger extraction, i.e. in the most recent work, event trigger extraction achieves 80.7%, while event arguments extraction achieves only 58%. In pipelined structures, the difficulty of event arguments extraction lies in its lack of classification feature, and the much higher computation consumption. In this work, we proposed a novel Event Extraction approach based on multi-layer Dilate Gated Convolutional Neural Network (EE-DGCNN) which has fewer parameters. In addition, enhanced local information is incorporated into word features, to assign event arguments roles for triggers predicted by the first subtask. The numerical experiments demonstrated significant performance improvement beyond state-of-art event extraction approaches on real-world datasets. Further analysis of extraction procedure is presented, as well as experiments are conducted to analyze impact factors related to the performance improvement.

Event extraction is an important research direction in the field of natural language processing (NLP) applications including information retrieval (IR). Traditional event extraction is realized with two methods: the pipeline and the joint extraction methods. The pipeline method determines the event by triggering word recognition to further implement event extraction and is prone to error cascading. The joint extraction method applies deep learning to implement the completion of the trigger word and the argument role classification task. Most studies with the joint extraction method adopt the CNN or RNN network structure. However, in the case of event extraction, deeper understanding of complex contexts is required. Existing studies do not make full use of syntactic relations. This paper proposes a novel event extraction model, which is built upon a Tree-LSTM network and a Bi-GRU network and carries syntactically related information. It is illustrated that this method simultaneously uses Tree-LSTM and Bi-GRU to obtain a representation of the candidate event sentence and identify the event type, which results in a better performance compared to the ones that use chain structured LSTM, CNN or only Tree-LSTM. Finally, the hidden state of each node is used in Tree-LSTM to predict a label for candidate arguments and identify/classify all arguments of an event. Lab results show that the proposed event extraction model achieves competitive results compared to previous works.

Event extraction is useful for many practical applications, such as news summarization and information retrieval. However, the popular automatic context extraction (ACE) event extraction program only defines very limited and coarse event schemas, which may not be suitable for practical applications. FrameNet is a linguistic corpus that defines complete semantic frames and frame-to-frame relations. As frames in FrameNet share highly similar structures with event schemas in ACE and many frames actually express events, we propose to redefine the event schemas based on FrameNet. Specifically, we extract frames expressing event information from FrameNet and leverage the frame-to-frame relations to build a hierarchy of event schemas that are more fine-grained and have much wider coverage than ACE. Based on the new event schemas, we propose a joint event extraction approach that leverages the hierarchical structure of event schemas and frame-to-frame relations in FrameNet. The extensive experiments have verified the advantages of our hierarchical event schemas and the effectiveness of our event extraction model. We further apply the results of our event extraction model on news summarization. The results show that the summarization approach based on our event extraction model achieves significant better performance than several state-of-the-art summarization approaches, which also demonstrates that the hierarchical event schemas and event extraction model are promising to be used in the practical applications.

Numerous important events happen everyday and everywhere but are reported in different media sources with different narrative styles. How to detect whether real-world events have been reported in articles and posts is one of the main tasks of event extraction. Other tasks include extracting event arguments and identifying their roles, as well as clustering and tracking similar events from different texts. As one of the most important research themes in natural language processing and understanding, event extraction has a wide range of applications in diverse domains and has been intensively researched for decades. This article provides a comprehensive yet up-to-date survey for event extraction from text. We not only summarize the task definitions, data sources and performance evaluations for event extraction, but also provide a taxonomy for its solution approaches. In each solution group, we provide detailed analysis for the most representative methods, especially their origins, basics, strengths and weaknesses. Last, we also present our envisions about future research directions.

With the rapid development of the Internet, the number of Internet users has grown rapidly, and the Internet has become more and more influential on people's lives. As a result, the amount of network text is increasing rapidly, and it is difficult to extract interested event information from it only by manual reading. Therefore, event extraction technique automatically extracting useful information from a large amount of unstructured texts becomes increasingly important. Event detection is the first step of event extraction task and plays a vital role in it. However, current event detection research lacks comprehensive consideration of the context of the trigger words. A Chinese event detection method based on multi-feature fusion and BiLSTM is proposed in this paper. The contextual information of word is divided into sentence-level and document-level in the method. The contextual information is captured based on BiLSTM model. At the same time, a word representation method suitable for trigger word classification tasks is proposed in this paper. The word representation incorporates semantic information, grammar information, and document-level context information of word. The word vectors in the sentence are sequentially inputted into BiLSTM model to obtain output vectors containing sentence-level contextual information. Finally, output vectors of BiLSTM are inputted into the Softmax classifier to realize the identification of the trigger words. The experimental results show that Chinese Event Detection Based on Multi-feature Fusion and BiLSTM method proposed in this paper has high accuracy.

In this article, we focus on the problem of social event extraction from Twitter, in which event detection, i.e., to identify which messages truly mention events of interest, is an indispensable step due to the fact that most Twitter messages, viz. tweets, are not related to any real-world event. Existing approaches to this problem often use pipelined architectures relying on some hand-crafted features derived using off-the-shelf natural language processing (NLP) tools, which may cause error propagation from the upstream component (event detection) to the downstream one (element extraction) and fail to leverage the interdependencies between them. To overcome these limitations, we propose a deep neural network based framework to Jointly Detect and Extract Events from Twitter (JDEET), which learns, as well as conducts, detection and extraction simultaneously by defining a joint loss function, a bidirectional long short-term memory (LSTM) based common representation layer, and a control gate. A conditional random field (CRF) layer is further employed to capture the strong dependencies among output labels. Experimental results show that the proposed approach outperforms the state-of-the-art ones considerably on a real-world dataset from Twitter.

Forecasting the stock market movements is an important and challenging task. As the Web information grows, researchers begin to extract effective indicators (e.g., the events and sentiments) from the Web to facilitate the prediction. However, the indicators obtained in previous studies are usually based on only one data source and thus may not fully cover the factors that can affect the stock market movements. In this paper, to improve the prediction for stock market composite index movements, we exploit the consistencies among different data sources, and develop a multi-source multiple instance model that can effectively combine events, sentiments, as well as the quantitative data into a comprehensive framework. To effectively capture the news events, we successfully apply a novel event extraction and representation method. Evaluations on the data from the year 2015 and 2016 demonstrate the effectiveness of our model. In addition, our approach is able to automatically determine the importance of each data source and identify the crucial input information that is considered to drive the movements, making the predictions interpretable.