Entity Tagging Research Articles

Medical Named Entity Recognition using Surrounding Sequences Matching

Since the development of information technologies, there is a huge amount of electronic documents that was written by medical specialists and are rich of useful information needed to make critical decisions in several medical tasks. Thus, a doctor must have a big knowledge and he is responsible for every decision he takes for patients. In fact, the doctor should read, with full concentration, many electronic narrative documents to collect the necessary information. Unfortunately, it's too tiring to read all necessary information about drugs, diseases and patient due to the large amount of documents that are increasing every day. Consequently, so many medical errors can happen and even can cause fatalities. On the other hand, information extraction is such a good field that can handle this problem. One of the most important main task in this field is the Named Entity Recognition (NER) and its role was to identify the medical named entities, such as drug, disease or treatment, from an unstructured text written in natural language. However, in order to treat the narrative text, natural language tasks should be performed before NER. In our paper, we introduce a named entity recognition method, called NESSMa (Named Entity tagging by Surrounding Sequence Matching), and based on sequence tagging, it is able to annotate the words of a sentence using Bidirectional Long Short-Term Memory neural network with Conditional Random Field (BiLSTM-CRF) model. We pass the Bidirectional Encoder Representations from Transformers (BERT) word embedding as feature together with the Part of Speech (PoS) of the word and the cue sequence information. The cue sequence information indicates if a word belongs to a named entity surrounding sequence based on word edit distance. For that, we have automatically constructed a dictionary of named entities’ surrounding sequences for each entity type using a train set. As expected, experiments shows that adding the cue sequence information is able to improve the results according to F1-measure and outperform state-of-the-art methods.

Development of Dialogue Management System for Banking Services

Rapid increase in conversational AI and user chat data lead to intensive development of dialogue management systems (DMS) for various industries. Yet, for low-resource languages, such as Azerbaijani, very little research has been conducted. The main purpose of this work is to experiment with various DMS pipeline set-ups to decide on the most appropriate natural language understanding and dialogue manager settings. In our project, we designed and evaluated different DMS pipelines with respect to the conversational text data obtained from one of the leading retail banks in Azerbaijan. In the work, the main two components of DMS—Natural language Understanding (NLU) and Dialogue Manager—have been investigated. In the first step of NLU, we utilized a language identification (LI) component for language detection. We investigated both built-in LI methods such as fastText and custom machine learning (ML) models trained on the domain-based dataset. The second step of the work was a comparison of the classic ML classifiers (logistic regression, neural networks, and SVM) and Dual Intent and Entity Transformer (DIET) architecture for user intention detection. In these experiments we used different combinations of feature extractors such as CountVectorizer, Term Frequency-Inverse Document Frequency (TF-IDF) Vectorizer, and word embeddings for both word and character n-gram based tokens. To extract important information from the text messages, Named Entity Extraction (NER) component was added to the pipeline. The best NER model was chosen among conditional random fields (CRF) tagger, deep neural networks (DNN), models and build in entity extraction component inside DIET architecture. Obtained entity tags fed to the Dialogue Management module as features. All NLU set-ups were followed by the Dialogue Management module that contains a Rule-based Policy to handle FAQs and chitchats as well as a Transformer Embedding Dialogue (TED) Policy to handle more complex and unexpected dialogue inputs. As a result, we suggest a DMS pipeline for a financial assistant, which is capable of identifying intentions, named entities, and a language of text followed by policies that allow generating a proper response (based on the designed dialogues) and suggesting the best next action.

Three birds, one stone: A novel translation based framework for joint entity and relation extraction

Joint entity and relation extraction is an important task in natural language processing and knowledge graph construction. Existing studies mainly focus on three issues: redundant predictions, overlapping triples and relation connections. However, as far as we know, none of them is able to solve the three problems simultaneously in a unified architecture. To address this issue, in this paper, we propose a novel translation based unified framework. Specifically, the proposed framework contains two components: an entity tagger and a relation extractor. The former is used to recognize all candidate head entities and tail entities respectively. The latter predicts relations for every entity pair dynamically through ranking with translation mechanism. To show the superiority of the proposed framework, we instantiate it through the simplest binary entity tagger and TransE algorithm. Extensive experiments over two widely used datasets demonstrate that, even with the simplest components, the proposed framework can still achieve competitive performance with most previous baselines. Moreover, the framework is flexible. It enjoys further performance boost when employing more powerful entity tagger and knowledge graph embedding algorithm.

Tagasaurus, a tool to assist manual image tagging and the creation of image collections

This paper presents Tagasaurus a tool to help manually annotate image sets and create annotated image collections. A key aspect of the workflow permitted by the interface is that it records independent emotional value associations, pictorial associations, and textual annotations. This version being showcased goes beyond previous approaches by allowing a user to create collections of images under an entity tag. This can help create a corpus of images under a specific label which is needed by machine learning models to train for classification of objects within the image scenes.

Named Entity Recognition on Software Requirements Specification Documents

Software Requirements Specifications (SRS) documents set the requirements and expectations of software development projects. This textual information is considered as a guideline for identifying various requirements for the developers. The content of an SRS document is concentrated around software requirement specific entities which can be used to improve software-based information retrieval systems. In this paper, we consider Named Entity Recognition (NER) over SRS documents and classify the software requirement specific entities using ML-based methods. Existing NER methods are typically restricted to four basic sets of entities that are not pertinent to NER in the software requirement domain. We define ten software requirement-based entities which cover the essence of the SRS documents. In order to predict the appropriate entity tags, we first create a limited feature set and experiment with various NER models including ML- based probabilistic models and DL models. We conduct a detailed numerical study to evaluate the effectiveness of the NER models over the SRS datasets. NER models with a basic feature set demonstrate promising performance with an F1-macro score of 81%. Our analysis shows that the entities can be extracted with high accuracy from the SRS documents, which then can be used for various purposes in practice such as extractive summarization of large SRS documents and effectively grouping the requirements.

NLM-Chem, a new resource for chemical entity recognition in PubMed full text literature

Automatically identifying chemical and drug names in scientific publications advances information access for this important class of entities in a variety of biomedical disciplines by enabling improved retrieval and linkage to related concepts. While current methods for tagging chemical entities were developed for the article title and abstract, their performance in the full article text is substantially lower. However, the full text frequently contains more detailed chemical information, such as the properties of chemical compounds, their biological effects and interactions with diseases, genes and other chemicals. We therefore present the NLM-Chem corpus, a full-text resource to support the development and evaluation of automated chemical entity taggers. The NLM-Chem corpus consists of 150 full-text articles, doubly annotated by ten expert NLM indexers, with ~5000 unique chemical name annotations, mapped to ~2000 MeSH identifiers. We also describe a substantially improved chemical entity tagger, with automated annotations for all of PubMed and PMC freely accessible through the PubTator web-based interface and API. The NLM-Chem corpus is freely available.

Technical Note: An embedding-based medical note de-identification approach with sparse annotation.

Medical note de-identification is critical for the protection of private information and the security of data sharing in collaborative research. The task demands the complete removal of all patient names and other sensitive information such as addresses and phone numbers from medical records. Accomplishing this goal is challenging, with many variations in the medical note formats and string representations. Existing de-identification approaches include pattern matching where extensive dictionary lists are constructed a prior; and entity tagging, which trains on a large word-wise annotated corpus. This motivates us to study an alternative to the existing approaches with a reduced annotation burden. In this work, we propose a novel approach that implicitly accounts for the language territory of sensitive information. Specifically, our approach incorporates a contextualized word embedding module and a multilayer perceptron to simultaneously infer the similarity of sensitive and non-sensitive vocabularies to a constructed landmark set, providing an overall sparsely supervised classification. To demonstrate the rationale, we present the principle and work pipeline with the task of name removal, but the proposed method applies to other strings as well. On a large cohort of hybrid clinical reports, including various forms of consulting, on-treatment-visit, and follow-up notes, we achieved >0.99 accuracies in our constructed training, validation, and testing sets. The sensitivity and specificity were 1.0 and 0.9973, respectively, for two randomly selected reports, comparing favorably to the benchmark Stanford NER tagger, which achieved 0.8529 and 0.9969. The F1 score was 0.889±0.046 and 0.822±0.103 across six randomly selected reports for the proposed method and the Stanford NER, respectively, and the result was significant under a one-sided t-test with alpha=0.1. Our qualitative and quantitative analysis shows that our method achieved better results than the pretrained 3-class Stanford NER toolbox.

Roconnaissance des Entités Nommées En Langues Peu Dotées En Utilisant La Représentation Distributionnelle Multiligue

Named Entity Recognition (NER) is a fundamental task in many NLP applications that seek to identify and classify expressions such as people, location, and organization names. Many NER systems have been developed, but the annotated data needed for good performances are not available for low-resource languages, such as Cameroonian languages. In this paper we exploit the low frequency of named entities in text to define a new suitable cross-lingual distributional representation for named entity recognition. We build the first Ewondo (a Bantu low-resource language of Cameroon) named entities recognizer by projecting named entity tags from English using our word representation. In terms of Recall, Precision and F-score, the obtained results show the effectiveness of the proposed distributional representation of words La reconnaissance des entités nommées (REN) est une tâche fondamentale du TALN dont le but est d'identifier les expressions telles que les noms de personnes, de lieux et d'organisations dans un texte. Il existe de nos jours plusieurs systèmes de REN, cependant les données nécessaires pour les utiliser dans le traitement des langues peu dotées telles que les langues camerounaises ne sont pas disponibles. Nous exploitons le fait que les entités nommées apparaissent rarement dans les textes pour définir une nouvelle représentation distributionnelle interlingue des mots, qui soit adaptée à la REN. En utilisant notre représentation, nous projectons les entités nommées de l'anglais vers l'ewondo (une langue bantou du Cameroun); nous obtenons donc le tout premier modèle de reconnaissance des entités nommées en langue ewondo. Les résultats en terme de précision, rappel et f-mesure montrent l'efficacité de notre représentation

MELODI Presto: a fast and agile tool to explore semantic triples derived from biomedical literature.

ABSTRACTSummaryThe field of literature-based discovery is growing in step with the volume of literature being produced. From modern natural language processing algorithms to high quality entity tagging, the methods and their impact are developing rapidly. One annotation object that arises from these approaches, the subject–predicate–object triple, is proving to be very useful in representing knowledge. We have implemented efficient search methods and an application programming interface, to create fast and convenient functions to utilize triples extracted from the biomedical literature by SemMedDB. By refining these data, we have identified a set of triples that focus on the mechanistic aspects of the literature, and provide simple methods to explore both enriched triples from single queries, and overlapping triples across two query lists.Availability and Implementationhttps://melodi-presto.mrcieu.ac.uk/.Supplementary information Supplementary data are available at Bioinformatics online.

A Korean named entity recognition method using Bi-LSTM-CRF and masked self-attention

Named entity recognition (NER) is a fundamental task in natural language processing. The existing Korean NER methods use the Korean morpheme, syllable sequence, and part-of-speech as features, and use a sequence labeling model to tackle this problem. In Korean, on one hand, morpheme itself contains strong indicative information of named entity (especially for time and person). On the other hand, the context of the target morpheme plays an important role in recognizing the named entity(NE) tag of the target morpheme. To make full use of these two features, we propose two auxiliary tasks. One of them is the morpheme-level NE tagging task which will capture the NE feature of syllable sequence composing morpheme. The other one is the context-based NE tagging task which aims to capture the context feature of target morpheme through the masked self-attention network. These two tasks are jointly trained with Bi-LSTM-CRF NER Tagger. The experimental results on Klpexpo 2016 corpus and Naver NLP Challenge 2018 corpus show that our model outperforms the strong baseline systems and achieves the state of the art.

Name the Name

Named Entity Recognition (NER), search, classification, and tagging of names and name like frequent informational elements in texts, has become a standard information extraction procedure for textual data. NER has been applied to many types of texts and different types of entities: newspapers, fiction, historical records, persons, locations, chemical compounds, protein families, animals etc. Performance of a NER system is usually quite heavily genre and domain dependent. Entity categories used in NER may also vary. The most used set of named entity categories is usually some version of three partite categorization of locations, persons, and organizations. In this paper we report evaluation results with data extracted from a digitized Finnish historical newspaper collection Digi using two statistical NER systems, namely, Stanford Named Entity Recognizer and LSTM-CRF NER model. The OCRed newspaper collection has lots of OCR errors; its estimated word level correctness is about 70–75%. Our NER evaluation collection and training data are based on ca. 500 000 words which have been manually corrected from OCR output of ABBYY FineReader 11. We have also available evaluation data of new uncorrected OCR output of Tesseract 3.04.01. Our Stanford NER results are mostly satisfactory. With our ground truth data we achieve F-score of 0.89 with locations and 0.84 with persons. With organizations the result is 0.60. With re-OCRed Tesseract output the results are 0.79, 0.72, and 0.42, respectively. Results of LSTM-CRF are similar.

Improving software bug-specific named entity recognition with deep neural network

There is a large volume of bug data in the bug repository, which contains rich bug information. Existing studies on bug data mining mainly rely on using information retrieval (IR) technology to search relevant historical bug reports. These studies basically treat a bug report as a closed unit, ignoring the semantic and structural information within it. Named-entity recognition (NER) is an important task of information extraction (IE) technology. Based on NER, fine-grained factual information could be comprehensively extracted to further form structured data, which provides a new way to improve the accessibility of bug information. However, bug NER is different from general NER tasks. Bug reports are free-form text, which include a mixed language environment studded with code, abbreviations and software-specific vocabularies. In this paper, we propose a deep neural network approach for bug-specific entity recognition called DBNER using bidirectional long short-term memory (LSTM) with Conditional Random Fields decoding model (CRF). DBNER extracts multiple features from the massive bug data and uses attention mechanism to improve the consistency of entity tags in the bug reports. Experiment results show that the F1-score reaches an average of 91.19%. In addition, in cross-project experiments, the DBNER’s F1-score reaches an average of 84%.

Fine Grained Named Entity Recognition via Seq2seq Framework

Fine-grained Named entity recognition (NER) is crucial to natural language processing (NLP) applications like relation extraction and knowledge graph construction. Most existing fine-grained NER systems suffer from inefficiency problem as they use manually annotated training datasets. To address such issue, our NER system could automatically generate datasets from Wikipedia in distant supervision paradigm through mapping hyperlinks in Wikipedia documents to Freebase. In addition, previous NER models can not effectively process fine-grained labels with more than 100 types. So we introduce a ‘BIO’ tagging strategy which can identify the position and type attributes simultaneously. Such tagging scheme transfers NER problem into a sequence-to-sequence (seq2seq) based issue. We propose a seq2seq framework to comprehend the input sentence in a comprehensive way. Specifically, we adopt a Bi-LSTM as the encoder to equally process the past and future information of the input. Then we add a self-attention mechanism to handle the long-term dependency problem in a long sequence. When classifying the entity tags, we choose CRF model as it adds more constraints to avoid position logical problem. Experiments are performed on large-scale datasets for fine-grained NER tasks. Experimental results verify the effectiveness of FSeqC, and it outperforms other state-of-the-art alternatives consistently and significantly.

Statistical Method for Named Entity Recognition in Telugu, an Indian Language

One of the important tasks of Natural Language Processing (NLP) is Named Entity Recognition (NER). The primary operation of NER is to identify proper nouns i.e. to locate all the named entities in the text and tag them as certain named entity categories such as Entity, Time expression and Numeric expression. In the previous works, NER for Telugu language is addressed with Conditional Random Fields (CRF) and Maximum Entropy models however they failed to handle ambiguous named entity tags for the same named entity. This paper presents a hybrid statistical system for Named Entity Recognition in Telugu language in which named entities are identified by both dictionary-based approach and statistical Hidden Markov Model (HMM). The proposed method uses Lexicon-lookup dictionary and contexts based on semantic features for predicting named entity tags. Further HMM is used to resolve the named entity ambiguities in predicted named entity tags. The present work reports an average accuracy of 86.3% for finding the named entities.

Deep Cascade Multi-Task Learning for Slot Filling in Online Shopping Assistant

Slot filling is a critical task in natural language understanding (NLU) for dialog systems. State-of-the-art approaches treat it as a sequence labeling problem and adopt such models as BiLSTM-CRF. While these models work relatively well on standard benchmark datasets, they face challenges in the context of E-commerce where the slot labels are more informative and carry richer expressions. In this work, inspired by the unique structure of E-commerce knowledge base, we propose a novel multi-task model with cascade and residual connections, which jointly learns segment tagging, named entity tagging and slot filling. Experiments show the effectiveness of the proposed cascade and residual structures. Our model has a 14.6% advantage in F1 score over the strong baseline methods on a new Chinese E-commerce shopping assistant dataset, while achieving competitive accuracies on a standard dataset. Furthermore, online test deployed on such dominant E-commerce platform shows 130% improvement on accuracy of understanding user utterances. Our model has already gone into production in the E-commerce platform.

A deep learning model incorporating part of speech and self-matching attention for named entity recognition of Chinese electronic medical records

BackgroundThe Named Entity Recognition (NER) task as a key step in the extraction of health information, has encountered many challenges in Chinese Electronic Medical Records (EMRs). Firstly, the casual use of Chinese abbreviations and doctors’ personal style may result in multiple expressions of the same entity, and we lack a common Chinese medical dictionary to perform accurate entity extraction. Secondly, the electronic medical record contains entities from a variety of categories of entities, and the length of those entities in different categories varies greatly, which increases the difficult in the extraction for the Chinese NER. Therefore, the entity boundary detection becomes the key to perform accurate entity extraction of Chinese EMRs, and we need to develop a model that supports multiple length entity recognition without relying on any medical dictionary.MethodsIn this study, we incorporate part-of-speech (POS) information into the deep learning model to improve the accuracy of Chinese entity boundary detection. In order to avoid the wrongly POS tagging of long entities, we proposed a method called reduced POS tagging that reserves the tags of general words but not of the seemingly medical entities. The model proposed in this paper, named SM-LSTM-CRF, consists of three layers: self-matching attention layer – calculating the relevance of each character to the entire sentence; LSTM (Long Short-Term Memory) layer – capturing the context feature of each character; CRF (Conditional Random Field) layer – labeling characters based on their features and transfer rules.ResultsThe experimental results at a Chinese EMRs dataset show that the F1 value of SM-LSTM-CRF is increased by 2.59% compared to that of the LSTM-CRF. After adding POS feature in the model, we get an improvement of about 7.74% at F1. The reduced POS tagging reduces the false tagging on long entities, thus increases the F1 value by 2.42% and achieves an F1 score of 80.07%.ConclusionsThe POS feature marked by the reduced POS tagging together with self-matching attention mechanism puts a stranglehold on entity boundaries and has a good performance in the recognition of clinical entities.

Beyond validation: Using programmed diagnostics to learn about, monitor, and successfully complete your DH project

Abstract Digital humanities projects have long relied on various schema languages—chiefly, RELAX NG and Schematron—for validating the XML documents in their data collections; however, these languages are limited in their ability to check for consistency, coherence, and completeness across the entire project. In our work as part of “Endings”, an umbrella project that comprises four diverse digital edition projects from different fields, we have developed a methodology for checking and enforcing correctness, completeness, and coherence across the entire document set. The following article describes the various stages (what we term “levels”) of our diagnostics process, all of which are driven by XSLT (Extensible Stylesheet Language Transformations) stylesheets, and produce a human readable report. These levels include checks for referential integrity, correct entity tagging, and potential duplicates in the data set. Using examples from the Endings projects, we show how diagnostic processes not only ensure correctness in the data set, but can also aid in determining project milestones and completion dates. Diagnostics, we argue, are thus a crucial extension to schema-based validation for complex digital projects and can provide concrete ways for digital humanities projects to enforce coherence and consistency and track their progress toward completion.

Neural architectures for open-type relation argument extraction

AbstractIn this work, we focus on the task of open-type relation argument extraction (ORAE): given a corpus, a query entity Q, and a knowledge base relation (e.g., “Q authored notable work with title X”), the model has to extract an argument of non-standard entity type (entities that cannot be extracted by a standard named entity tagger, for example, X: the title of a book or a work of art) from the corpus. We develop and compare a wide range of neural models for this task yielding large improvements over a strong baseline obtained with a neural question answering system. The impact of different sentence encoding architectures and answer extraction methods is systematically compared. An encoder based on gated recurrent units combined with a conditional random fields tagger yields the best results. We release a data set to train and evaluate ORAE, based on Wikidata and obtained by distant supervision.

Analyzing the Tagging Quality of the Spanish OpenStreetMap

In this paper, a framework for the assessment of the quality of OpenStreetMap is presented, comprising a batch of methods to analyze the quality of entity tagging. The approach uses Taginfo as a reference base and analyses quality measures such as completeness, compliance, consistence, granularity, richness and trust . The framework has been used to analyze the quality of OpenStreetMap in Spain, comparing the main cities of Spain. Also a comparison between Spain and some major European cities has been carried out. Additionally, a Web tool has been also developed in order to facilitate the same kind of analysis in any area of the world.

Character Embedding for Language Identification in Hindi-English Code-mixed Social Media Text

Social media platforms are now widely used by the people to express their opinion or interest. The language used by the users in social media earlier was purely English. Code-mixed text, i.e., mixing of two or more languages, is commonly seen now. Incode-mixed data, one language will be written using another language script. So to process such code-mixed text, identification of language used in each word is important for language processing. The main objective of the work is to propose a technique for identifying the language of Hindi-English code-mixed data used in three social media platforms namely, Facebook, Twitter, and WhatsApp. The classification of Hindi-English code-mixed data into Hindi, English, Named Entity, Acronym, Universal, Mixed (Hindi along with English)and Undefined tags were performed. Popular word embedding features were used for the representation of each word. Two kinds of embedding features were considered - word-based embedding features and character-based context features. The proposed method was done with the addition of context information along with the embedding features. A well-known machine learning classifier, Support Vector Machine was used to train and test the system. The work on Language Identification in code-mixed text using character-based embedding is a novel approach and shows promising results.