FGCAN: Filter-based Gated Contextual Attention Network for event detection

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.

Context information brings new opportunities for efficient and effective system resource management of mobile devices. In this work, we focus on the use of context information to achieve energy-efficient, ubiquitous wireless connectivity. Our field-collected data show that the energy cost of network interfaces poses a great challenge to ubiquitous connectivity, despite decent availability of cellular networks. We propose to leverage the complementary strengths of Wi-Fi and cellular interfaces by automatically selecting the most efficient one based on context information. We formulate the selection of wireless interfaces as a statistical decision problem. The challenge is to accurately estimate Wi-Fi network conditions without powering up the network interface. We explore the use of different context information, including time, history, cellular network conditions, and device motion, to statistically estimate Wi-Fi network conditions with negligible overhead. We evaluate several context-based algorithms for the estimation and prediction of current and future network conditions. Simulations using field-collected traces show that our network estimation algorithms can improve the average battery lifetime of a commercial mobile phone for an ECG reporting application by 40 percent, very close to the estimated theoretical upper bound of 42 percent. Furthermore, our most effective algorithm can predict Wi-Fi availability for one and ten hours into the future with 95 and 90 percent accuracy, respectively.

The task of event detection aims to find the event trigger for a sentence and identify the correct event type. Contextual information is crucial to event detection, which helps a model to identify the triggers better. Existing models utilizing contextual information only take document information as additional features for deep learning model, without considering the specific contribution of document information to trigger classification. In this paper, we propose a Document-Improved Hierarchical Modular Event Detection (DIHMED) model to extract hierarchical contextual information. Specifically, considering the relevance between event types, we build independent modules that combine the document-level information to express this relevance. Given the fact that events from the same document are often related, these modules can make better use of document-level information. We conduct several experiments on a Chinese political event dataset and the results show that our model can outperform the state-of-the-art models.

Semi-supervised named entity recognition in multi-level contexts

The legal sector remains distinctive due to the complex language structure and specialized terminology of legal data. This complexity offers considerable contextual information, which demands natural language processing (NLP). The availability of high-quality and well-structured legal datasets is essential for advancing NLP research and applications within the legal field. However, a gap exists within the Arabic legal NLP owing to insufficient research and datasets. To address this gap, we aim to propose an Arabic legal case dataset containing cases, case summaries, relevant keywords, and case categories. The legal case data were obtained from the Board of Grievances website in Saudi Arabia and include 3170 cases distributed across 47 classes. The number of words in these cases varies significantly, ranging from about 100 to nearly 30,000 words per case. Moreover, the number of pages varies, ranging from one page to 80 pages per case. Therefore, this dataset supports various NLP applications, including text categorization, data extraction, sentiment analysis, and summarization, thereby improving task efficiency and decision accuracy in the legal profession.

The need for improving the robustness and the ability to adapt to different operational conditions is a key requirement for a wider deployment of robots in many application domains. To this end, uses of contextual information have proven to be effective in many robotic applications. In this paper, we present a case study on the use of contextual information for rescue robots. The goal is to show that contextual information can be used to improve the system performance, by dynamically tailoring the functionalities of the robot to the specific features of the situation at hand. The case study includes several experiments, both in simulation and on a real robot, which address two core tasks in rescue applications: navigation and mapping.

Chinese named entity recognition (NER) has been an important problem in natural language processing (NLP) field. Most existing methods mainly use traditional deep learning models which cannot fully leverage contextual dependencies that are very important for capturing the relations between words or characters for modeling. To address this problem, various language representation methods such as BERT have been proposed to learn the global context information. Although these methods can achieve good results, the large number of parameters limited the efficiency and application in real-world scenarios. To improve both of the performance and efficiency, this paper proposes an ALBERT-based Chinese NER method which uses ALBERT, a Lite version of BERT, as the pre-trained model to reduce model parameters and to improve the performance through sharing cross-layer parameters. Besides, it uses conditional random field (CRF) to capture the sentence-level correlation information between words or characters to alleviate the tagging inconsistency problems. Experimental results demonstrate that our method outperforms the comparison methods over 4.23–11.17% in terms of relative F1-measure with only 4% of BERT’s parameters.

BackgroundProgression-free survival (PFS) is a crucial endpoint in cancer drug research. Clinician-confirmed cancer progression, namely real-world PFS (rwPFS) in unstructured text (ie, clinical notes), serves as a reasonable surrogate for real-world indicators in ascertaining progression endpoints. Response evaluation criteria in solid tumors (RECIST) is traditionally used in clinical trials using serial imaging evaluations but is impractical when working with real-world data. Manual abstraction of clinical progression from unstructured notes remains the gold standard. However, this process is a resource-intensive, time-consuming process. Natural language processing (NLP), a subdomain of machine learning, has shown promise in accelerating the extraction of tumor progression from real-world data in recent years.ObjectivesWe aim to configure a pretrained, general-purpose health care NLP framework to transform free-text clinical notes and radiology reports into structured progression events for studying rwPFS on metastatic breast cancer (mBC) cohorts.MethodsThis study developed and validated a novel semiautomated workflow to estimate rwPFS in patients with mBC using deidentified electronic health record data from the Nference nSights platform. The developed workflow was validated in a cohort of 316 patients with hormone receptor–positive, human epidermal growth factor receptor-2 (HER-2) 2-negative mBC, who were started on palbociclib and letrozole combination therapy between January 2015 and December 2021. Ground-truth datasets were curated to evaluate the workflow’s performance at both the sentence and patient levels. NLP-captured progression or a change in therapy line were considered outcome events, while death, loss to follow-up, and end of the study period were considered censoring events for rwPFS computation. Peak reduction and cumulative decline in Patient Health Questionnaire-8 (PHQ-8) scores were analyzed in the progressed and nonprogressed patient subgroups.ResultsThe configured clinical NLP engine achieved a sentence-level progression capture accuracy of 98.2%. At the patient level, initial progression was captured within ±30 days with 88% accuracy. The median rwPFS for the study cohort (N=316) was 20 (95% CI 18-25) months. In a validation subset (n=100), rwPFS determined by manual curation was 25 (95% CI 15-35) months, closely aligning with the computational workflow’s 22 (95% CI 15-35) months. A subanalysis revealed rwPFS estimates of 30 (95% CI 24-39) months from radiology reports and 23 (95% CI 19-28) months from clinical notes, highlighting the importance of integrating multiple note sources. External validation also demonstrated high accuracy (92.5% sentence level; 90.2% patient level). Sensitivity analysis revealed stable rwPFS estimates across varying levels of missing source data and event definitions. Peak reduction in PHQ-8 scores during the study period highlighted significant associations between patient-reported outcomes and disease progression.ConclusionsThis workflow enables rapid and reliable determination of rwPFS in patients with mBC receiving combination therapy. Further validation across more diverse external datasets and other cancer types is needed to ensure broader applicability and generalizability.

Seeing words in context: the interaction of lexical and sentence level information during reading

CD-CARS: Cross-domain context-aware recommender systems

The Use of Contextual Information Related to General World Knowledge by Right Brain-Damaged Individuals in Pronoun Resolution

In the last decade there has been a considerable development of spaceborne SAR sensors. All the major space agencies are planning future SAR missions with polarimetric capabilities. However there is still a need to guide electromagnetic and statistics theories that take advantage of this kind of information towards operational applications. The use of contextual information is often required for automatic interpretation and target detection. The implementation of fast and reliable algorithms that exploit both polarimetric and contextual information can be limited by the increased dimensionality of the problem. Principal Component Analysis (PCA) is a data analysis technique that relies on a simple transformation of recorded observation, stored in a vector, to produce statistically independent variables. Non-Linear PCA is commonly seen as a non-linear generalization and extension of standard PCA. If non-linear correlations between variables exist, NLPCA will describe the data with greater accuracy and/or by fewer factors than PCA. In this work a combination of polarimetric and contextual information is performed using an Auto Associative Neural Network. A set of polarimetric input features were chosen together with contextual descriptors in order to produce an information set having lower dimensionality that can be exploited in a classification problem.

The existing YOLOv5‐based framework has achieved great success in the field of target detection. However, in forest fire detection tasks, there are few high‐quality forest fire images available, and the performance of the YOLO model has suffered a serious decline in detecting small‐scale forest fires. Making full use of context information can effectively improve the performance of small target detection. To this end, this paper proposes a new graph‐embedded YOLOv5 forest fire detection framework, which can improve the performance of small‐scale forest fire detection using different scales of context information. To mine local context information, we design a spatial graph convolution operation based on the message passing neural network (MPNN) mechanism. To utilize global context information, we introduce a multi‐head self‐attention (MSA) module before each YOLO head. The experimental results on FLAME and our self‐built fire dataset show that our proposed model improves the accuracy of small‐scale forest fire detection. The proposed model achieves high performance in real‐time performance by fully utilizing the advantages of the YOLOv5 framework.

Chinese word segmentation is the basis of the Chinese natural language processing (NLP). With the development of the deep learning, various neural network models are applied to the Chinese word segmentation. However, current neural network models have the characteristics of artificial feature extraction, nonstandard word-weight, inability to effectively use long-distance information and long training time of models in Chinese word segmentation. To solve a series of problems, this article presents a CNN-Bidirectional GRU-CRF neural network model (CNN Bidirectional GRU CRF Network, CBiGCN), which breaks through the limit of conventional method window, truly realizes end-to-end processing and applies to the neural network model by the five-Tag set method, bias-variable-weight greedy strategy and supplements by Goldstein-Armijo guidelines. Besides, this model, with simple structure, is easy to be operated. And it can automatically learn features, reduces large amounts of tasks on specific knowledge in the form of handcrafted features and data pre-processing, makes use of context information effectively. The authors set an experiment with two data corpuses for Chinese word segmentation to evaluate their system. The experiment verified their new model can obtain better Chinese word segmentation results and greatly reduce training time.

e19062 Background: The annual incidence of venous thromboembolism (VTE) is roughly 50-fold increased post allogeneic hematopoietic cell transplant (HSCT). Timely detection of VTE events has a significant impact on morbidity and mortality from these events. Manual chart review is commonly used for detection of VTE events; however, this is labor intensive and often not feasible. The International Classification of Diseases, 10th revision (ICD-10) has attempted to codify VTE more easily but has high false positive and false negative rates. Natural language processing (NLP) algorithms have been designed to improve detection of VTE events in electronic medical record systems over the past several years. This study aims to compare the accuracy of our institution’s NLP algorithm to the ICD-10 in detecting extremity VTE/pulmonary embolism (PE) events in hematopoietic stem cell transplant (HSCT) patients. Methods: This study was a retrospective analysis of adult patients who had allogeneic HSCT at MD Anderson between 2016-2020. Patient charts were assessed by three different methods for acute VTE events within 100 days of HSCT (index date). ICD-10 codes and our institution’s NLP algorithm were used separately to identify these VTE events. Afterwards, manual chart review was performed for confirmation. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated for the ICD-10, NLP, and the NLP+ICD combination. Results: A total of 1,391 patient charts were analyzed in our study. There were 129 (9.3%) VTE events detected via manual chart review. Three methodologies were used for comparison: the NLP algorithm alone, the ICD code alone, and detection by NLP or ICD. The NLP algorithm alone had the best specificity (98.9%) and PPV (89.4%) of the three methods. The ICD-10 code had a statistically significant decrease in ability to detect acute VTE events compared to the NLP (p<0.001) (Table). Of the 19 VTE events not identified by NLP, all were found in radiology or vascular laboratory reports. Conclusions: Our study shows the overall superior performance of the NLP algorithm, as it had higher sensitivity, specificity, PPV, and NPV compared to the ICD-10, as well as a better specificity and PPV compared to the combination of both methods. Future refinement of the NLP algorithm and combination with other detection methodologies will allow for more accurate detection of VTE in large cohorts. [Table: see text]