Natural Language Processing Module Research Articles

Implementing a routine and standard approach for the automatic collection of socio-economic impact observations for impact-based forecasting and warning

Globally, there are different scientific methods being developed to support the provision of Impact-based Forecasts and Warnings. Impact data is critically valuable to many of these methods enabling the development of new hazard impact models and forecasting applications, and the evaluation of these different products. However, routine and consistent approaches to collect socio-economic impact information remain challenging, with traditional approaches being labour intensive, error prone and unsustainable. This paper describes the design of an automated workflow that can collect, standardise, and harmonise impact observations from a range of sources, routinely. The workflow is a 6-step process including web scraping, Natural Language Processing (NLP) and geoparsing. The workflow enables essential criteria (i.e., date, location, types and details of the societal impacts and the hazard(s) which led to them) to be captured faster than previous manual approaches. It also allows a wider range of hazard and impact types to be collected than was previously practical to do. Testing of the workflow indicates that it could benefit from further refinement of the NLP and geoparse modules to allow for the detection of finer scale impact locations. This in turn would allow for different scales of event detection to be developed and tested. Additionally, the applicability of the workflow for different types of impact data sources such as news and social media remains to be tested. Despite the need for further refinement, this workflow represents a step change in the speed and efficiency of impact data collection within the Met Office.

Natural Language Processing for the Ascertainment and Phenotyping of Left Ventricular Hypertrophy and Hypertrophic Cardiomyopathy on Echocardiogram Reports

Extracting and accurately phenotyping electronic health documentation is critical for medical research and clinical care. We sought to develop a highly accurate and open-source natural language processing (NLP) module to ascertain and phenotype left ventricular hypertrophy (LVH) and hypertrophic cardiomyopathy (HCM) diagnoses fromechocardiogram reports within a diverse hospital network. After the initial development on 17,250 echocardiogram reports, 700 unique reports from 6 hospitals were randomly selected from data repositories within the Mass General Brigham healthcare system and manually adjudicated by physicians for 10 subtypes of LVH and diagnoses of HCM. Using an open-source NLP system, the module was formally tested on 300 training set reports and validated on 400 reports. The sensitivity, specificity, positive predictive value, and negative predictive value were calculated to assess the discriminative accuracy of the NLP module. The NLP demonstrated robust performance across the 10 LVH subtypes, with the overall sensitivity and specificity exceeding 96%. In addition, the NLP module demonstrated excellent performance in detecting HCM diagnoses, with sensitivity and specificity exceeding 93%. In conclusion, we designed a highly accurate NLP module to determine the presence of LVH and HCM on echocardiogram reports. Our work demonstrates the feasibility and accuracy of NLP to detect diagnoses on imaging reports, even when described in free text. This module has been placed in the public domain to advance research, trial recruitment, and population health management for patients with LVH-associated conditions.

DeepPhe-CR: Natural Language Processing Software Services for Cancer Registrar Case Abstraction.

Manual extraction of case details from patient records for cancer surveillance is a resource-intensive task. Natural Language Processing (NLP) techniques have been proposed for automating the identification of key details in clinical notes. Our goal was to develop NLP application programming interfaces (APIs) for integration into cancer registry data abstraction tools in a computer-assisted abstraction setting. We used cancer registry manual abstraction processes to guide the design of DeepPhe-CR, a web-based NLP service API. The coding of key variables was performed through NLP methods validated using established workflows. A container-based implementation of the NLP methods and the supporting infrastructure was developed. Existing registry data abstraction software was modified to include results from DeepPhe-CR. An initial usability study with data registrars provided early validation of the feasibility of the DeepPhe-CR tools. API calls support submission of single documents and summarization of cases across one or more documents. The container-based implementation uses a REST router to handle requests and support a graph database for storing results. NLP modules extract topography, histology, behavior, laterality, and grade at 0.79-1.00 F1 across multiple cancer types (breast, prostate, lung, colorectal, ovary, and pediatric brain) from data of two population-based cancer registries. Usability study participants were able to use the tool effectively and expressed interest in the tool. The DeepPhe-CR system provides an architecture for building cancer-specific NLP tools directly into registrar workflows in a computer-assisted abstraction setting. Improved user interactions in client tools may be needed to realize the potential of these approaches.

Constructing a disease database and using natural language processing to capture and standardize free text clinical information

The ability to extract critical information about an infectious disease in a timely manner is critical for population health research. The lack of procedures for mining large amounts of health data is a major impediment. The goal of this research is to use natural language processing (NLP) to extract key information (clinical factors, social determinants of health) from free text. The proposed framework describes database construction, NLP modules for locating clinical and non-clinical (social determinants) information, and a detailed evaluation protocol for evaluating results and demonstrating the effectiveness of the proposed framework. The use of COVID-19 case reports is demonstrated for data construction and pandemic surveillance. The proposed approach outperforms benchmark methods in F1-score by about 1–3%. A thorough examination reveals the disease’s presence as well as the frequency of symptoms in patients. The findings suggest that prior knowledge gained through transfer learning can be useful when researching infectious diseases with similar presentations in order to accurately predict patient outcomes.

Conversational Intelligent Chatbot for Placement Service

Nowadays it becomes very difficult to get placed in an organization which will perfectly suits to your profile because of the huge number of competition and lack of knowledge. Most of the students are not able to take a right decision at starting point of their career which always becomes first step towards their goals. The main aim of this project is to build a conversational AI Chatbot model which will interact with students who are walking through placement activities as well as students who are in a situation dealing with job related issues after completion of their respected degree's. This conversational AI will act as a human for the user and will help the user to resolve their queries and get a clear vision. For this we have used Dialog Flow, a Natural Language Processing (NLP) module to translate students’ queries during conversation in order to understand their intension. Information related to placement activities is provided to students. Key Word: Conversational AI chatbot, queries, placement activities, dialog flow, Kore.ai, Natural Language Processing.

Price Negotiating Chatbot on E-Commerce Website Using NPL

This proposes the development of a price negotiating chatbot on e-commerce websites using Natural Language Processing (NLP) technology. The chatbot aims to assist customers in negotiating prices with the sellers, enhancing their shopping experience. The proposed chatbot will be built using the Python programming language and the TensorFlow library for Natural Language Processing. The chatbot's architecture consists of several components, including a user interface, an NLP module, a price prediction module, and a negotiation module. The NLP module will enable the chatbot to understand and interpret the customer's messages, while the price prediction module will predict the minimum price that the seller is willing to accept. The negotiation module will use reinforcement learning algorithms to negotiate with the seller and come up with the best possible price for the customer. The proposed chatbot will provide customers with a convenient way to negotiate prices with sellers, enhancing their shopping experience. The chatbot's architecture, which includes a user interface, an NLP module, a price prediction module, and a negotiation module, will enable the chatbot to understand and interpret customer messages and negotiate prices with sellers on behalf of the customer. The chatbot will be trained and assessed on a substantial dataset of negotiation conversations, and its performance will be compared to other contemporary negotiation models. The results will demonstrate that the proposed chatbot significantly improves the shopping experience of customers, attaining higher success rates, shorter negotiation times, and increased customer.

Inquiring Natural Language Processing Capabilities on Robotic Systems through Virtual Assistants: A Systemic Approach

This paper attempts to approach the interface of a robot from the perspective of virtual assistants. Virtual assistants can also be characterized as the mind of a robot, since they manage communication and action with the rest of the world they exist in. Therefore, virtual assistants can also be described as the brain of a robot and they include a Natural Language Processing (NLP) module for conducting communication in their human-robot interface. This work is focused on inquiring and enhancing the capabilities of this module. The problem is that nothing much is revealed about the nature of the human-robot interface of commercial virtual assistants. Therefore, any new attempt of developing such a capability has to start from scratch. Accordingly, to include corresponding capabilities to a developing NLP system of a virtual assistant, a method of systemic semantic modelling is proposed and applied. For this purpose, the paper briefly reviews the evolution of virtual assistants from the first assistant, in the form of a game, to the latest assistant that has significantly elevated their standards. Then there is a reference to the evolution of their services and their continued offerings, as well as future expectations. The paper presents their structure and the technologies used, according to the data provided by the development companies to the public, while an attempt is made to classify virtual assistants, based on their characteristics and capabilities. Consequently, a robotic NLP interface is being developed, based on the communicative power of a proposed systemic conceptual model that may enhance the NLP capabilities of virtual assistants, being tested through a small natural language dictionary in Greek.

USQA: A User Story Quality Analyzer prototype for supporting software engineering students

AbstractThe Standish Group Reports 83.9% of IT Projects fail, and one of the top factors in failed projects is the incomplete requirements or user stories. Therefore, it is essential to teach undergraduate students from computer science degree programs how to create complete user stories. Computer science programs include some subjects or topics involving requirements or user stories collection and writing, such as Requirements Engineering, Software Engineering, Project Management, or Quality Software Assurance. For that reason, we designed a web application called User Story Quality Analyzer (USQA) that uses Natural Language Processing modules to detect errors regarding aspects of usefulness, completeness, and polysemes in the user stories creation. The tool was proved from three perspectives: (1) a reliability test, where 35 user stories developed by experts were tested in the app to prove the prototype's reliability; (2) usability and utility analysis; 48 students interacted with the tool and responded a Satisfaction Usability Scale and an open‐ended question, the students reported a high usability score; (3) finally, error classification, we gathered 159 user stories processed by the system, and we classified the students' common errors considering incompleteness and polysemes. After the evaluations, we concluded that USQA could evaluate the user stories as an expert, which could help the professors/teachers/instructors in their courses by providing feedback to the students when they are writing user stories.

Plot-aware transformer for recommender systems

<abstract> <p>Plot text is very valuable supporting information in movie recommendations. It has several characteristics: 1) It is rich in content. Each movie often has a document of more than 200 words to describe it, which can give the movie a rich semantic meaning. 2) Objectivity. Plot texts are different from review information. A movie may have thousands of reviews with mixed and conflicting opinions. However, a film has only one plot text, which is fair in tone and does not take a position. Despite its appealing properties and potential for accurate movie portrayal, the lack of a building block for effectively mining plot semantics has led to the marginalization of plot text in the design of movie recommendation algorithms. Therefore, in this paper, we explore the application of the Transformer, currently the best natural language processing module, to learning movie plot texts to help achieve more accurate rating prediction. We propose the "Plot-Aware Transformer" model (PAT) to model the process of "user-movie" rating interaction. We test the PAT model on several movie datasets and demonstrated that the model is competitive. In all tasks, PAT achieves state-of-the-art performance compared to baseline experiments.</p> </abstract>

Экспериментальное моделирование базы данных сбалансированного лингвистического корпуса

The research aims to build a functioning experimental model of a relational database for operating with a balanced linguistic corpus of a fiction work. Scientific novelty lies in the fact that for the first time within the framework of a humanities study, a database of a linguistic corpus is being modeled with a thorough description and taking into account technical details and based on the provisions of the author’s concept of professionally oriented programming. The work involved three stages: forming a technical task (the structure of two tables of a relational database was developed, the SQLite format was selected, additional columns of the tables were provided for the subsequent expansion of the content of research), writing the source code for creating and filling the database (the Python programming language and the spaCy natural language processing module were used) and testing it based on the material of the texts of three F. Kafka’s novels “The Castle”, “Amerika” and “The Trial” (three functioning databases were created). The research findings have shown that modern natural language processing software tools allow one to create automatically full-fledged databases for processing SQL queries, which can be further expanded manually or automatically.

Natural Language Semantic Answering: Application to Medicinal Plants and Coronavirus

This paper describes PryRe (Preguntas y Respuestas) {Questions and answers}, a question answering system that receives as input a question in Spanish and returns the answer. An information retrieval algorithm identifies the meaning of the question using its semantic properties. To do this, it is necessary to implement natural language processing modules. PryRe identifies the question using a triplet R (C, V), where R is the relation or link, C is the concept or main idea, and V is the value of the concept. For example, in the question: ¿Cuál es la hierba que mejora la digestion? {What is the herb that improves digestion?}, the answer is Manzanilla {Chamomile}. To obtain this response, a process of query analysis and design is executed. The analysis consists of identifying the answer, we call this process the semantic identification of the question. The PryRe algorithms are explained in detail. The tests have been carried out with some sources on herbalism [15] and on 2019-nCoV [14] in an Ontology; they show an acceptable accuracy of 83%. Resources used in this work are (1) the OM notation, which is used to describe ontologies, and (2) the deductive capability of PryRe. PryRe consults this ontology to answer the questions using cases that are described in its algorithm.

Recognition of visual scene elements from a story text in Persian natural language

AbstractText-to-scene conversion systems map natural language text to formal representations required for visual scenes. The difficulty involved in this mapping is one of the most critical challenges for developing these systems. The current study mapped Persian natural language text as the headmost system to a conceptual scene model. This conceptual scene model is an intermediate semantic representation between natural language and the visual scene and contains descriptions of visual elements of the scene. It will be used to produce meaningful animation based on an input story in this ongoing study. The mapping task was modeled as a sequential labeling problem, and a conditional random field (CRF) model was trained and tested for sequential labeling of scene model elements. To the best of the authors’ knowledge, no dataset for this task exists; thus, the required dataset was collected for this task. The lack of required off-the-shelf natural language processing modules and a significant error rate in the available corpora were important challenges to dataset collection. Some features of the dataset were manually annotated. The results were evaluated using standard text classification metrics, and an average accuracy of 85.7% was obtained, which is satisfactory.

Architecture of project management web services based on integration with natural language processing modules

A method for intellectualizing project management web services based on integration with natural language processing modules is proposed. The supporting of high reliability, extensibility and flexibility of the interface of such systems is a necessary condition for the providing of effective tools for developers of software systems of various profiles. It is shown that a prevalent trend in software development is to increase the portability of software in order to ensure the possibility of using the same application in different runtime environments. The advantages of using the concept of “API-first” are highlighted. The features of the “API-first” web server architecture are considered, in which all requests for web services are executed through a single web API interface, and the resource-intensive web pages formation is transferred to a separate structure on the same host or to a separate web server. The advantages of using natural language processing tools to improve the efficiency and availability of project management web services are considered. Project management web service database structure is proposed. All the natural language processing data for the conversational interface consist of user intents list, entities collections list, entities (collocations or word sets). It will be stored within each external language processing web service in the appropriate format automatically. Examples of prototype business logic with functions for the internal and external API are shown. Most of the external natural language processing service handlers are closely related to this business logic.

Software architecture of the question-answering subsystem with elements of self-learning

Within the framework of this paper, the analysis of software systems of question-answering type and their basic architectures has been carried out. With the development of machine learning technologies, creation of natural language processing (NLP) engines, as well as the rising popularity of virtual personal assistant programs that use the capabilities of speech synthesis (text-to-speech), there is a growing need in developing question-answering systems which can provide personalized answers to users' questions. All modern cloud providers proposed frameworks for organization of question answering systems but still we have a problem with personalized dialogs. Personalization is very important, it can put forward additional demands to a question-answering system’s capabilities to take this information into account while processing users’ questions. Traditionally, a question-answering system (QAS) is developed in the form of an application that contains a knowledge base and a user interface, which provides a user with answers to questions, and a means of interaction with an expert. In this article we analyze modern approaches to architecture development and try to build system from the building blocks that already exist on the market. Main criteria for the NLP modules were: support of the Ukrainian language, natural language understanding, functions of automatic definition of entities (attributes), ability to construct a dialogue flow, quality and completeness of documentation, API capabilities and integration with external systems, possibilities of external knowledge bases integration After provided analyses article propose the detailed architecture of the question-answering subsystem with elements of self-learning in the Ukrainian language. In the work you can find detailed description of main semantic components of the system (architecture components)

Natural language processing for the assessment of cardiovascular disease comorbidities: The cardio-Canary comorbidity project.

Objective: Accurate ascertainment of comorbidities is paramount in clinical research. While manual adjudication is labor‐intensive and expensive, the adoption of electronic health records enables computational analysis of free‐text documentation using natural language processing (NLP) tools.Hypothesis: We sought to develop highly accurate NLP modules to assess for the presence of five key cardiovascular comorbidities in a large electronic health record system.Methods: One‐thousand clinical notes were randomly selected from a cardiovascular registry at Mass General Brigham. Trained physicians manually adjudicated these notes for the following five diagnostic comorbidities: hypertension, dyslipidemia, diabetes, coronary artery disease, and stroke/transient ischemic attack. Using the open‐source Canary NLP system, five separate NLP modules were designed based on 800 “training‐set” notes and validated on 200 “test‐set” notes.Results: Across the five NLP modules, the sentence‐level and note‐level sensitivity, specificity, and positive predictive value was always greater than 85% and was most often greater than 90%. Accuracy tended to be highest for conditions with greater diagnostic clarity (e.g. diabetes and hypertension) and slightly lower for conditions whose greater diagnostic challenges (e.g. myocardial infarction and embolic stroke) may lead to less definitive documentation.Conclusion: We designed five open‐source and highly accurate NLP modules that can be used to assess for the presence of important cardiovascular comorbidities in free‐text health records. These modules have been placed in the public domain and can be used for clinical research, trial recruitment and population management at any institution as well as serve as the basis for further development of cardiovascular NLP tools.

Crowdsourcing Ecologically-Valid Dialogue Data for German

Despite their increasing success, user interactions with smart speech assistants (SAs) are still very limited compared to human-human dialogue. One way to make SA interactions more natural is to train the underlying natural language processing modules on data which reflects how humans would talk to a SA if it was capable of understanding and producing natural dialogue given a specific task. Such data can be collected applying a Wizard-of-Oz approach (WOz), where user and system side are played by humans. WOz allows researchers to simulate human-machine interaction while benefitting from the fact that all participants are human and thus dialogue-competent. More recent approaches have leveraged simple templates specifying a dialogue scenario for crowdsourcing large-scale datasets. Template-based collection efforts, however, come at the cost of data diversity and naturalness. We present a method to crowdsource dialogue data for the SA domain in the WOz framework, which aims at limiting researcher-induced bias in the data while still allowing for a low-resource, scalable data collection. Our method can also be applied to languages other than English (in our case German), for which fewer crowd-workers may be available. We collected data asynchronously, relying only on existing functionalities of Amazon Mechanical Turk, by formulating the task as a dialogue continuation task. Coherence in dialogues is ensured, as crowd-workers always read the dialogue history, and as a unifying scenario is provided for each dialogue. In order to limit bias in the data, rather than using template-based scenarios, we handcrafted situated scenarios which aimed at not pre-script-ing the task into every single detail and not priming the participants’ lexical choices. Our scenarios cued people’s knowledge of common situations and entities relevant for our task, without directly mentioning them, but relying on vague language and circumlocutions. We compare our data (which we publish as the CROWDSS corpus; n = 113 dialogues) with data from MultiWOZ, showing that our scenario approach led to considerably less scripting and priming and thus more ecologically-valid dialogue data. This suggests that small investments in the collection setup can go a long way in improving data quality, even in a low-resource setup.

Spark NLP: Natural Language Understanding at Scale

<h2>Abstract</h2> Spark NLP is a Natural Language Processing (NLP) library built on top of Apache Spark ML. It provides simple, performant & accurate NLP annotations for machine learning pipelines that can scale easily in a distributed environment. Spark NLP comes with 1100+ pretrained pipelines and models in more than 192+ languages. It supports nearly all the NLP tasks and modules that can be used seamlessly in a cluster. Downloaded more than 2.7 million times and experiencing 9x growth since January 2020, Spark NLP is used by 54% of healthcare organizations as the world's most widely used NLP library in the enterprise.

Semantic Task Planning for Service Robots in Open Worlds

This paper presents a planning system based on semantic reasoning for a general-purpose service robot, which is aimed at behaving more intelligently in domains that contain incomplete information, under-specified goals, and dynamic changes. First, Two kinds of data are generated by Natural Language Processing module from the speech: (i) action frames and their relationships; (ii) the modifier used to indicate some property or characteristic of a variable in the action frame. Next, the task’s goals are generated from these action frames and modifiers. These goals are represented as AI symbols, combining world state and domain knowledge, which are used to generate plans by an Answer Set Programming solver. Finally, the plan’s actions are executed one by one, and continuous sensing grounds useful information, which makes the robot use contingent knowledge to adapt to dynamic changes and faults. For each action in the plan, the planner gets its preconditions and effects from domain knowledge, so during the execution of the task, the environmental changes, especially those conflict with the actions, not only the action being performed but also the subsequent actions, can be detected and handled as early as possible. A series of case studies are used to evaluate the system and verify its ability to acquire knowledge through dialogue with users, solve problems with the acquired causal knowledge, and plan for complex tasks autonomously in the open world.

Automated Metric Analysis of Spanish Poetry: Two Complementary Approaches

The automatic metric analysis (commonly referred to as scansion ) of Spanish poetry is not a trivial problem since it combines the nuances of the language, the different poetic traditions related to melodic patterns, and the personal stylistic preferences and intentions of the author. In this paper, we explore two alternative algorithmic approaches tailored to different applications scenarios. The first approach, Rantanplan, is a rule-based method that consists of four Natural Language Processing modules that work together to perform scansion and other related analysis: Part of Speech tagging, syllabification, stress assignment, and metrical adjustment. The second approach, Jumper, explores the possibility of performing scansion without syllabification, with a twofold purpose: to minimize the errors propagated in different parts of the linguistic processing pipeline (including the syllabification step), and to improve the efficiency of the process. Both systems outperform the state of the art and provide either a more informative solution (suitable, for instance, for teaching purposes) or a more efficient processing (when a correct scansion is all the linguistic knowledge required, as in scholar philological studies). The combined use of both systems turns out to provide a practical tool to clean-up manual annotation errors in corpora.

Islamic view towards Bitcoin

This paper proposes to analyze the agent behavior by means of big data extracted from the search engine « Google trends » and Twitter API to visualize the emotions and the manner of thinking about « Bitcoin » in the Islamic context. Two kinds of sentiment measures are constructed. The first is based on the search query of the word « Bitcoin » with religious connotation all over the world from 14/04/2017 to 14/04/2018 in weekly frequency. The second is built on twitter data from 03/04/2018 to 13/04/2018, by using a Bayesian machine learning device exploiting deep natural language processing modules to assign emotions and sentiment orientations. In the next step, the Granger causality analysis is used to investigate the hypothesis that this sentiment causes the volatility and the returns of « Bitcoin ». The results show that, at a first-level that twitter users of the word « Islamic Bitcoin » improve positive sentiment. Secondly, the Twitter sentiment measure has a significant effect on lagged Bitcoin returns and volatility. Furthermore, this sentimental variable Granger causes Bitcoin returns and volatility. This study contributes to the literature by studying the influence of the doctrinal view towards Bitcoin on his prices dynamics. Knowing that Bitcoin is a new financial asset and there is a large debate on his compliance with shariah