Search results

The purpose of this paper is to present a system for recognition of location names in ancient books written in languages, such as Chinese, in which proper names are not signaled by an initial capital letter.

Rule-based and statistical methods were combined to develop a set of rules for identification of product-related location names in the local chronicles of Guangdong. A name recognition system, with functions of document management, information extraction and storage, rule management, location name recognition, and inquiry and statistics, was developed using Microsoft's .NET framework, SQL Server 2005, ADO.NET and XML. The system was evaluated with precision ratio, recall ratio and the comprehensive index, F.

The system was quite successful at recognizing product-related location names (F was 71.8 percent), demonstrating the potential for application of automatic named entity recognition techniques in digital collation of ancient books such as local chronicles.

Results suffered from limitations in initial digitization of the text. Statistical methods, such as the hidden Markov model, should be combined with an extended set of recognition rules to improve recognition scores and system efficiency.

Electronic access to local chronicles by location name saves time for chorographers and provides researchers with new opportunities.

Named entity recognition brings previously isolated ancient documents together in a knowledge base of scholarly and cultural value.

Automatic name recognition can be implemented in information extraction from ancient books in languages other than English. The system described here can also be adapted to modern texts and other named entities.

The purpose of this paper is to propose an extensible framework for extracting data set usage from research articles.

The framework uses a training set of manually labeled examples to identify word features surrounding data set usage references. Using the word features and general entity identifiers, candidate data sets are extracted and scored separately at the sentence and document levels. Finally, the extracted data set references can be verified by the authors using a web-based verification module.

This paper successfully addresses a significant gap in entity extraction literature by focusing on data set extraction. In the process, this paper: identified an entity-extraction scenario with specific characteristics that enable a multiphase approach, including a feasible author-verification step; defined the search space for word feature identification; defined scoring functions for sentences and documents; and designed a simple web-based author verification step. The framework is successfully tested on 178 articles authored by researchers from a large research organization.

Whereas previous approaches focused on completely automated large-scale entity recognition from text snippets, the proposed framework is designed for a longer, high-quality text, such as a research publication. The framework includes a verification module that enables the request validation of the discovered entities by the authors of the research publications. This module shares some similarities with general crowdsourcing approaches, but the target scenario increases the likelihood of meaningful author participation.

The purpose of this paper is to provide a methodology for automatic annotation of a multimedia collection of intangible cultural heritage mostly in the form of interviews. Assigned annotations provide a way to search the collection.

Annotation is based on automatic extraction of metadata and is conducted by named entity and topic extraction from textual descriptions with a rule-based approach supported by vocabulary resources, a compiled domain-specific classification scheme and domain-oriented corpus analysis.

The proposed methodology for automatic annotation of a collection of intangible cultural heritage, applied on the cultural heritage of the Balkans, has very good results according to F measure, which is 0.87 for the named entity and 0.90 for topic annotation. The overall methodology enables encapsulating domain-specific and language-specific knowledge into collections of finite state transducers and allows further improvements.

Although cultural heritage has a significant role in the development of identity of a group or an individual, it is one of those specific domains that have not yet been fully explored in case of many languages. A methodology is proposed that can be used for incorporating natural language processing techniques into digital libraries of cultural heritage.

By mapping-out the capabilities, challenges and limitations of named-entity recognition (NER), this article aims to synthesise the state of the art of NER in the context of the early modern research field and to inform discussions about the kind of resources, methods and directions that may be pursued to enrich the application of the technique going forward.

Through an extensive literature review, this article maps out the current capabilities, challenges and limitations of NER and establishes the state of the art of the technique in the context of the early modern, digitally augmented research field. It also presents a new case study of NER research undertaken by Enlightenment Architectures: Sir Hans Sloane's Catalogues of his Collections (2016–2021), a Leverhulme funded research project and collaboration between the British Museum and University College London, with contributing expertise from the British Library and the Natural History Museum.

Currently, it is not possible to benchmark the capabilities of NER as applied to documents of the early modern period. The authors also draw attention to the situated nature of authority files, and current conceptualisations of NER, leading them to the conclusion that more robust reporting and critical analysis of NER approaches and findings is required.

This article examines NER as applied to early modern textual sources, which are mostly studied by Humanists. As addressed in this article, detailed reporting of NER processes and outcomes is not necessarily valued by the disciplines of the Humanities, with the result that it can be difficult to locate relevant data and metrics in project outputs. The authors have tried to mitigate this by contacting projects discussed in this paper directly, to further verify the details they report here.

The authors suggest that a forum is needed where tools are evaluated according to community standards. Within the wider NER community, the MUC and ConLL corpora are used for such experimental set-ups and are accompanied by a conference series, and may be seen as a useful model for this. The ultimate nature of such a forum must be discussed with the whole research community of the early modern domain.

NER is an algorithmic intervention that transforms data according to certain rules-, patterns- or training data and ultimately affects how the authors interpret the results. The creation, use and promotion of algorithmic technologies like NER is not a neutral process, and neither is their output A more critical understanding of the role and impact of NER on early modern documents and research and focalization of some of the data- and human-centric aspects of NER routines that are currently overlooked are called for in this paper.

This article presents a state of the art snapshot of NER, its applications and potential, in the context of early modern research. It also seeks to inform discussions about the kinds of resources, methods and directions that may be pursued to enrich the application of NER going forward. It draws attention to the situated nature of authority files, and current conceptualisations of NER, and concludes that more robust reporting of NER approaches and findings are urgently required. The Appendix sets out a comprehensive summary of digital tools and resources surveyed in this article.

The purpose of this paper is to focus on the problem of named entity disambiguation. The paper disambiguates named entities on a very detailed level. To each entity is assigned a concrete identifier of a corresponding Wikipedia article describing the entity.

For such a fine‐grained disambiguation a correct representation of the context is crucial. The authors compare various context representations: bag of words representation, linguistic representation and structured co‐occurrence representation. Models for each representation are described and evaluated. They also investigate the possibilities of multilingual named entity disambiguation.

Based on this evaluation, the structured co‐occurrence representation provides the best disambiguation results. It showed up that this method could be successfully applied also on other languages, not only on English.

Despite its good results the structured co‐occurrence context representation has several limitations. It trades precision for recall, which might not be desirable in some use cases. Also it is not able to disambiguate two different types of entities, which are mentioned under the same name in the same text. These limitations can be overcome by combination with other described methods.

The authors provide a ready‐made web service, which can be directly plugged in existing applications using a REST interface.

The paper proposes a new approach to named entity disambiguation exploiting various context representation models (bag of words, linguistic and structural representation). The authors constructed a comprehensive dataset based on all English Wikipedia articles for named entity disambiguation. They evaluated and compared the individual context representation models on this dataset. They evaluate the support of multiple languages.

The purpose of this study was to design a multitask learning model so that biomedical entities can be extracted without having any ambiguity from biomedical texts.

In the proposed automated bio entity extraction (ABEE) model, a multitask learning model has been introduced with the combination of single-task learning models. Our model used Bidirectional Encoder Representations from Transformers to train the single-task learning model. Then combined model's outputs so that we can find the verity of entities from biomedical text.

The proposed ABEE model targeted unique gene/protein, chemical and disease entities from the biomedical text. The finding is more important in terms of biomedical research like drug finding and clinical trials. This research aids not only to reduce the effort of the researcher but also to reduce the cost of new drug discoveries and new treatments.

As such, there are no limitations with the model, but the research team plans to test the model with gigabyte of data and establish a knowledge graph so that researchers can easily estimate the entities of similar groups.

As far as the practical implication concerned, the ABEE model will be helpful in various natural language processing task as in information extraction (IE), it plays an important role in the biomedical named entity recognition and biomedical relation extraction and also in the information retrieval task like literature-based knowledge discovery.

During the COVID-19 pandemic, the demands for this type of our work increased because of the increase in the clinical trials at that time. If this type of research has been introduced previously, then it would have reduced the time and effort for new drug discoveries in this area.

In this work we proposed a novel multitask learning model that is capable to extract biomedical entities from the biomedical text without any ambiguity. The proposed model achieved state-of-the-art performance in terms of precision, recall and F1 score.

In computational chemistry, the chemical bond energy (pKa) is essential, but most pKa-related data are submerged in scientific papers, with only a few data that have been extracted by domain experts manually. The loss of scientific data does not contribute to in-depth and innovative scientific data analysis. To address this problem, this study aims to utilize natural language processing methods to extract pKa-related scientific data in chemical papers.

Based on the previous Bert-CRF model combined with dictionaries and rules to resolve the problem of a large number of unknown words of professional vocabulary, in this paper, the authors proposed an end-to-end Bert-CRF model with inputting constructed domain wordpiece tokens using text mining methods. The authors use standard high-frequency string extraction techniques to construct domain wordpiece tokens for specific domains. And in the subsequent deep learning work, domain features are added to the input.

The experiments show that the end-to-end Bert-CRF model could have a relatively good result and can be easily transferred to other domains because it reduces the requirements for experts by using automatic high-frequency wordpiece tokens extraction techniques to construct the domain wordpiece tokenization rules and then input domain features to the Bert model.

By decomposing lots of unknown words with domain feature-based wordpiece tokens, the authors manage to resolve the problem of a large amount of professional vocabulary and achieve a relatively ideal extraction result compared to the baseline model. The end-to-end model explores low-cost migration for entity and relation extraction in professional fields, reducing the requirements for experts.

The output of academic literature has increased significantly due to digital technology, presenting researchers with a challenge across every discipline, including materials science, as it is impossible to manually read and extract knowledge from millions of published literature. The purpose of this study is to address this challenge by exploring knowledge extraction in materials science, as applied to digital scholarship. An overriding goal is to help inform readers about the status knowledge extraction in materials science.

The authors conducted a two-part analysis, comparing knowledge extraction methods applied materials science scholarship, across a sample of 22 articles; followed by a comparison of HIVE-4-MAT, an ontology-based knowledge extraction and MatScholar, a named entity recognition (NER) application. This paper covers contextual background, and a review of three tiers of knowledge extraction (ontology-based, NER and relation extraction), followed by the research goals and approach.

The results indicate three key needs for researchers to consider for advancing knowledge extraction: the need for materials science focused corpora; the need for researchers to define the scope of the research being pursued, and the need to understand the tradeoffs among different knowledge extraction methods. This paper also points to future material science research potential with relation extraction and increased availability of ontologies.

To the best of the authors’ knowledge, there are very few studies examining knowledge extraction in materials science. This work makes an important contribution to this underexplored research area.

Safety management plays an important part in coal mine construction. Due to complex data, the implementation of the construction safety knowledge scattered in standards poses a challenge. This paper aims to develop a knowledge extraction model to automatically and efficiently extract domain knowledge from unstructured texts.

Bidirectional encoder representations from transformers (BERT)-bidirectional long short-term memory (BiLSTM)-conditional random field (CRF) method based on a pre-training language model was applied to carry out knowledge entity recognition in the field of coal mine construction safety in this paper. Firstly, 80 safety standards for coal mine construction were collected, sorted out and marked as a descriptive corpus. Then, the BERT pre-training language model was used to obtain dynamic word vectors. Finally, the BiLSTM-CRF model concluded the entity’s optimal tag sequence.

Accordingly, 11,933 entities and 2,051 relationships in the standard specifications texts of this paper were identified and a language model suitable for coal mine construction safety management was proposed. The experiments showed that F1 values were all above 60% in nine types of entities such as security management. F1 value of this model was more than 60% for entity extraction. The model identified and extracted entities more accurately than conventional methods.

This work completed the domain knowledge query and built a Q&A platform via entities and relationships identified by the standard specifications suitable for coal mines. This paper proposed a systematic framework for texts in coal mine construction safety to improve efficiency and accuracy of domain-specific entity extraction. In addition, the pretraining language model was also introduced into the coal mine construction safety to realize dynamic entity recognition, which provides technical support and theoretical reference for the optimization of safety management platforms.

The majority of existing studies about named entity recognition (NER) concentrate on the prediction enhancement of deep neural network (DNN)-based models themselves, but the issues about the scarcity of training corpus and the difficulty of annotation quality control are not fully solved, especially for Chinese ancient corpora. Therefore, designing a new integrated solution for Chinese historical NER, including automatic entity extraction and man-machine cooperative annotation, is quite valuable for improving the effectiveness of Chinese historical NER and fostering the development of low-resource information extraction.

The research provides a systematic approach for Chinese historical NER with a three-stage framework. In addition to the stage of basic preprocessing, the authors create, retrain and yield a high-performance NER model only using limited labeled resources during the stage of augmented deep active learning (ADAL), which entails three steps—DNN-based NER modeling, hybrid pool-based sampling (HPS) based on the active learning (AL), and NER-oriented data augmentation (DA). ADAL is thought to have the capacity to maintain the performance of DNN as high as possible under the few-shot constraint. Then, to realize machine-aided quality control in crowdsourcing settings, the authors design a stage of globally-optimized automatic label consolidation (GALC). The core of GALC is a newly-designed label consolidation model called simulated annealing-based automatic label aggregation (“SA-ALC”), which incorporates the factors of worker reliability and global label estimation. The model can assure the annotation quality of those data from a crowdsourcing annotation system.

Extensive experiments on two types of Chinese classical historical datasets show that the authors’ solution can effectively reduce the corpus dependency of a DNN-based NER model and alleviate the problem of label quality. Moreover, the results also show the superior performance of the authors’ pipeline approaches (i.e. HPS + DA and SA-ALC) compared to equivalent baselines in each stage.

The study sheds new light on the automatic extraction of Chinese historical entities in an all-technological-process integration. The solution is helpful to effectively reducing the annotation cost and controlling the labeling quality for the NER task. It can be further applied to similar tasks of information extraction and other low-resource fields in theoretical and practical ways.