Results for “Language” — Page 40

NASA NTRS2022

FPP: A Modeling Language for F Prime

We present F Prime Prime (FPP), a new open-source modeling language for F Prime. F Prime is an open-source flight software framework developed at JPL and deployed, among other places, on the Mars helicopter Ingenuity. FPP provides a convenient way to model the architectural elements of an F Prime application, e.g., components, ports, and their connections. It has a succinct and readable syntax, a well- defined semantics, and robust error checking and reporting. The FPP tool suite, written in Scala, analyzes FPP models, reports errors, and translates correct FPP models to a combination of XML and C++. Existing F Prime tools translate the XML to a partial implementation in C++, to be completed by the developers. The model elements have clean interfaces and are highly reusable. An accompanying visualization tool constructs diagrams of components and connections that FSW developers can use to understand and communicate their designs, for ex- ample at reviews. We discuss the design and implementation of FPP and the integration of FPP into F Prime. We also discuss our experience using FPP to construct F Prime models. Finally, we discuss our plans for future work, including improved code generation, improved visualization, and more advanced analysis capabilities.

Starch, Michael D.↗

NASA NTRSDate not supplied

Digital Assistance for System Requirement Discovery and Analysis using Machine Learning Natural Language Processing Algorithm

NASA’s Air Traffic Management-Exploration (ATM-X) Urban Air Mobility (UAM) Airspace Subproject is conducting research that evolves UAM airspace towards a highly automated and operationally flexible system of the future (see https://www.nasa.gov/uam-overview/ for more information). The complexity of UAM airspace, and its evolution through a series of transformative epochs, requires a planning tool to effectively organize, integrate, and communicate the research that will guide the evolution of UAM operations in the National Airspace System (NAS). The planning tool, called the UAM airspace research roadmap (or just roadmap), is being developed as a new system engineering methodology leveraging model based system engineering (MBSE) and machine learning natural language processing (ML NLP, or just NLP) capabilities. This presentation gives an overview of the NLP application within this system engineering methodology and will describe how it is being used to meet the ATM-X UAM Airspace Subproject’s overarching research goals.

ATM↗

NASA NTRSDate not supplied

Composable Semantic Frames for Grounding Language in Robot Control Primitives

As robots become increasingly capable of taking on challenging tasks, we want robots to be commanded in intuitive ways. Non-expert users in particular should be able to communicate with robots about task goals. As a result, modes of interaction such as language have gained interest for commanding robots. We present composable semantic frames, which ground commands in robot control primitives by composing high-level commands from lower-level commands. We demonstrate that composable semantic frames allow robots to understand and execute a variety of challenging commands, such as those involving multiple verb meanings, command variations, and compound nouns. The robot quickly processes composable semantic frames and accurately grounds and executes the commanded tasks, demonstrating the power of composable semantic frames for allowing users to intuitively interact with robots.

Emily Sheetz↗

NASA NTRS2022

Virtual Assistant for First Responders Using Natural Language Understanding and Optical Character Recognition

Commercial deep learning capabilities are available for many applications such as computer vision processing and intelligent chat bots. The Google Cloud Platform product Google Dialogflow provides lifelike conversational artificial intelligence (AI) using machine learning (ML) to generate natural conversations between computers and humans. This ML utilizes natural language understanding (NLU) to recognize a user’s intent and extracts key information into a form of entities. We have developed a user-friendly application through understanding the hazardous material database, first aid safety guidelines and observing the process of first responders who access this information in the field. We created the Trusted and Explainable Artificial Intelligence for Saving Lives (TruePAL) virtual assistant using Dialogflow1 and TensorFlow2 paired with EasyOCR.3 The chatbot supports first responders by providing voice interaction which helps limit additional steps such as browsing through multiple categories when searching for information. Using feedback from our field interviews, the voice interface has been developed to enable the first responder to focus on the immediate emergency. With less distractions, the first responder is able to engage the incident more effectively. The partial hands-free TruePAL chatbot assistant improves the accessibility to the correct guidance by an average of 1.9 seconds compared to the widely used application, NIH WISER, which requires full attention to operate. We combined this intelligent chatbot with a separate visual processing capability to produce hazardous signage analysis and generate the proper guidance for first responders. With the evolving functionality of AI tools, the use of virtual assistants in first responder technology will be an advancement, benefiting the safety of both first responders and civilians.

Chow, Edward↗

NASA NTRSDate not supplied

From BERTopic to SysML: Informing Model-Based Failure Analysis With Natural Language Processing for Complex Aerospace Systems

The development of emerging complex aerospace systems will require new approaches for capturing safety incident scenarios as early as possible in the design phase. However, for novel systems, relevant data available is limited. In this work, we propose a framework informing model-based mission assurance activities with historical incident reports, lessons learned, or other relevant engineering documents using natural language processing. In doing so, we investigate whether there is useful information in data sets that are relevant, if not identical, to the system under design and whether, through rigorous systems engineering practice, this information can be effectively leveraged through model-based failure analysis. In a worked case study, we apply state-of-the-art topic modeling techniques to two data sets, a mission relevant data set and a system relevant data set. The sets of topics are merged and interpreted to form a preliminary list of failure topics that can be used to inform the identification of off-nominal modes in the model-based failure modes and effects analysis development. Once data from the system in operation is available, it can be used to update the topics identified. By extracting information about likely failures from relevant historical data sets and utilizing model-based mission assurance to ensure relevance and rigor, unanticipated failures can be reduced, and projects can more effectively learn from past missions.

Failure Analysis↗

NASA NTRSDate not supplied

From BERTopic to SysML: Informing Model-Based Failure Analysis With Natural Language Processing for Complex Aerospace Systems

The development of emerging complex aerospace systems will require new approaches for capturing safety incident scenarios as early as possible in the design phase. However, for novel systems, relevant data available is limited. In this work, we propose a framework informing model-based mission assurance activities with historical incident reports, lessons learned, or other relevant engineering documents using natural language processing. In doing so, we investigate whether there is useful information in data sets that are relevant, if not identical, to the system under design and whether, through rigorous systems engineering practice, this information can be effectively leveraged through model-based failure analysis. In a worked case study, we apply state-of-the-art topic modeling techniques to two data sets, a mission relevant data set and a system relevant data set. The sets of topics are merged and interpreted to form a preliminary list of failure topics that can be used to inform the identification of off-nominal modes in the model-based failure modes and effects analysis development. Once data from the system in operation is available, it can be used to update the topics identified. By extracting information about likely failures from relevant historical data sets and utilizing model-based mission assurance to ensure relevance and rigor, unanticipated failures can be reduced, and projects can more effectively learn from past missions.

Failure Analysis↗

NASA NTRSDate not supplied

Classification of Notices to Airmen using Natural Language Processing

This paper establishes the feasibility of using Natural Language Processing (NLP) to classify NOTAMs or Notices to Airmen – a pilot messaging framework to gather real-time situational awareness. Present day air mobility operations heavily rely on NOTAMs. However, pilots often have difficulty interpreting NOTAMs due to the sheer volume of inapplicable messages and unclear abbreviations. Using NLP, the presented study analyzes the accuracy of classifying NOTAMs and, thereby, the efficiency of generating actionable interpretations in real time. To this effect, efficacies of four NLP neural network architectures were analyzed, including three Recurrent Neural Networks (RNNs) with GloVe, Word2Vec, and FastText word embeddings, and one trained Bi-Directional Encoder Representations from Transformers (BERT) model. The four neural networks were trained and evaluated on three open-source datasets of varying text lengths, vocabularies, and grammars, taken from e-commerce product descriptions, social media tweets, and unstructured descriptions for data and analytics services on open data marketplaces such as NASA’s Data and Reasoning Fabric (DRF) platform. This provided cross-analysis of each neural network architecture’s performance per text type. The best performing architecture, BERT, was then fine-tuned on a collection of open-source NOTAM data. Post-training, a real-time NOTAM classification service was implemented to draw inference on new NOTAMs using the trained model, which demonstrated close to 99% accuracy in classification. This modular classification service is envisioned to be integrated with a data and analytics delivery platform, such as the DRF, thus availing real-time contextualization of NOTAMs to air mobility clients, humans, and machines for enhanced decision making.

Aiden C. Szeto↗

NASA NTRSDate not supplied

Classification of Notices to Airmen using Natural Language Processing

This paper establishes the feasibility of using Natural Language Processing (NLP) to classify NOTAMs or Notices to Airmen – a pilot messaging framework to gather real-time situational awareness. Present day air mobility operations heavily rely on NOTAMs. However, pilots often have difficulty interpreting NOTAMs due to the sheer volume of inapplicable messages and unclear abbreviations. Using NLP, the presented study analyzes the accuracy of classifying NOTAMs and, thereby, the efficiency of generating actionable interpretations in real time. To this effect, efficacies of four NLP neural network architectures were analyzed, including three Recurrent Neural Networks (RNNs) with GloVe, Word2Vec, and FastText word embeddings, and one trained Bi-Directional Encoder Representations from Transformers (BERT) model. The four neural networks were trained and evaluated on three open-source datasets of varying text lengths, vocabularies, and grammars, taken from e-commerce product descriptions, social media tweets, and unstructured descriptions for data and analytics services on open data marketplaces such as NASA’s Data and Reasoning Fabric (DRF) platform. This provided cross-analysis of each neural network architecture’s performance per text type. The best performing architecture, BERT, was then fine-tuned on a collection of open-source NOTAM data. Post-training, a real-time NOTAM classification service was implemented to draw inference on new NOTAMs using the trained model, which demonstrated close to 99% accuracy in classification. This modular classification service is envisioned to be integrated with a data and analytics delivery platform, such as the DRF, thus availing real-time contextualization of NOTAMs to air mobility clients, humans, and machines for enhanced decision making.

Aiden Szeto↗

NASA NTRSDate not supplied

Identifying Human Errors and Error Mechanisms From Accident Reports Using Large Language Models

Emerging operational concepts for aviation hinge on novel paradigms for human machine interaction. Critical to their safe operation is early consideration of human error into the design process. Existing methods for consideration of human error require significant expert input, which is challenging both in early design and in novel systems for which there is little existing safety expertise. In this research, we propose a methodology for identifying human error, error producing factors, and mechanisms in early design from historical incident reports. Additionally, we hypothesize that cross-domain sharing of lessons learned can aid with early design human considerations in circumstances where data is not relevant or incomplete. This is addressed by identifying causes of human error in aviation and railway domains through applying state-of-the art natural language processing techniques to historical incident reports. Using this method, it is possible to extract extensive reports on human error from past incidents. Using the proposed approach, we identify nine human errors from railway reports and fourteen from aviation reports, with three errors common to both domains. There is at least one error producing conditions for each human error while a majority of the errors have more than one error mechanism. We also found that a majority of the human errors, error producing factors, and error mechanisms (even if they are not common between the domains) can be used to inform safe operations across domains as long as the errors are not domain specific and are interpreted and contextualized using engineering judgement.

Human Errors↗

NASA NTRS2024

Analyzing EOSDIS Dataset Research Outputs using Knowledge Graphs and Large Language Models

Datasets, unlike publications, can be updated over time, with each new version receiving a DOI but not always being linked to previous ones. This complicates tracking citations across a dataset’s lifecycle. We address this by integrating dataset versions and citations into a knowledge graph (KG), which helps trace dataset citations and analyze dataset usage in applied research. To categorize publications from various journals, we fine-tuned NASA IMPACT INDUS Large Language Model (LLM) on a labeled publication set, assigning publications to one of twenty applied research areas. By linking datasets to these research areas, we improved dataset searchability and discovery through these domains.

open-source↗

NASA NTRSDate not supplied

Discovering Research Areas in Dataset Applications Through Knowledge Graphs and Large Language Models

Scientific datasets are increasingly cited in peer-reviewed journal publications, facilitating easy access to research utilizing those datasets. Datasets undergo a life cycle where older versions of datasets are replaced by newer versions often due to improvements in data resolution, algorithms, and other factors. Unlike peer reviewed documents registered with a single Digital Unique Identifier (DOI), datasets can be updated over time and the newer version of the datasets are registered with a new DOI which is not necessarily linked to the previous version of the dataset. It is challenging when publications citing a dataset need to be traced over the entire life cycle of that dataset. We provide an innovative approach to link the dataset versions and publications using a knowledge graph (KG). KG can help to trace the dataset cited in publications over the entire dataset life cycle and shed light into dataset usage in various applied research areas. We fine-tuned the pretrained NASA IMPACTINDUS Large Language Model (LLM) on a set of labeled publications abstracts. Our results showed that 87% of the publications were classified into one of twenty applied research areas, while the remaining 13% were classified into non-applied research areas. By linking datasets to applied research areas through the KG and employing Global Change Master Directory(GCMD), a well-established controlled vocabulary of scientific keywords describing Earth science datasets, we contribute to a transparent and advanced search and discovery mechanism for datasets across the Earth data ecosystem. The integrated KG and LLM approach is now incorporated and operational in dataset publication management at one of NASA’s Earth science data archival centers.

data provenance↗

NASA NTRSDate not supplied

Enhancing Dataset Discovery and Usage Tracking in Earth Sciences: Integrating Knowledge Graphs and Large Language Models

NASA's Data Active Archive Centers (DAACs) have played a crucial role in supporting a wide range of applied research in Earth and Environmental sciences. To date, over 20,000 publications have been collected, citing more than 3,000 NASA Earth science datasets. We present an innovative approach that links datasets and collected publications through a knowledge graph (KG). This KG enables the tracking of dataset citations throughout the dataset's lifecycle, revealing patterns of dataset usage across various applied research areas. We fine-tuned the pre-trained NASA IMPACT INDUS-Base Retriever Large Language Model (LLM) using a set of labeled publication abstracts. Our results indicate that 87% of the publications were classified into one of twenty applied research areas, while the remaining 13% were categorized into non-applied research areas. The classified publications linked to datasets are used to discover datasets by users interested in specific applied research and by dataset providers to determine dataset usage for applications.

open-source↗

DOE OSTI2014

HERCULES/PL: The Pattern Language of HERCULES

Interrogating the structure of a program for patterns of interest is attractive to the broader spectrum of software engineering. The very approach by which a pattern is constructed remains a concern for the source code mining community. This paper presents a pattern programming model, for the C and Fortran programming languages, using a compiler directives approach. We discuss our specification, called HERCULES/PL, throughout a number of examples and show how different patterns can be constructed, plus some preliminary results.

Kartsaklis, Christos↗

DOE OSTI2017

Modular Expression Language for Ordinary Differential Equation Editing

MELODEEis a system for describing systems of initial value problem ordinary differential equations, and a compiler for the language that produces optimized code to integrate the differential equations. Features include rational polynomial approximation for expensive functions and automatic differentiation for symbolic jacobians

Blake, Robert C.↗

DOE OSTI2021

Cybersecurity Training Curriculum Analysis through the application of Machine Learning Text Classification and Natural Language Processing

In the domain of cybersecurity, there are a wide variety of education and training courses offered by a variety of training providers (commercial vendors, governmental, and academic institutions). Unfortunately, a comprehensive cross-provider mapping of the body of course offerings does not currently exist. Furthermore, although individual providers have made efforts, an accepted cross-provider mapping of education and training courses (or categories) to an accepted framework of work-roles by cybersecurity work-role and competency level has not yet been developed. The inability to compare training courses by topic or cybersecurity work-role and the level of difficulty (competency level) affects all organizations in identifying and selecting potential training opportunities for their personnel performing cybersecurity duties. In this work, we report on our application of Machine Learning (ML) Text Classification and Natural Language Processing (NLP) methodologies to begin to create a process to organize an accurate and thorough catalog of course offerings by work-role and competency level. Through the analysis of text-based course attributes (description, learning objectives, prerequisites, etc.) along with the text-based attributes for identified cybersecurity work-roles, our ML efforts examined methods to determine the work-role "best-fit" for each course as well as the competency level through action-verb text comparison.

99 GENERAL AND MISCELLANEOUS↗

DOE OSTI2016

Development of Criteria for Hardware Descripted Language Programmed-Devices for Safety Systems in Nuclear Power Plants in the U.S

The U.S. Nuclear Regulatory Commission (NRC) is in the process of developing a regulatory guide (RG) describing a method the staff of the NRC considers acceptable, for use in complying with NRC regulations with respect to the development of hardware description language-programmed device (HPD). Examples include: field programmable gate arrays (FPGAs), systems in the power, instrumentation, and control portions of safety systems for nuclear power plants. The regulatory framework that NRC is establishing for nuclear power plants consists of a number of regulations and supporting guidelines applicable to the development of HPD-based safety systems. The NRC issues RGs to describe to the public, methods that the NRC staff considers acceptable for use in implementing specific parts of the agency's regulations; to explain techniques that the NRC staff uses in evaluating specific problems or postulated accidents; and to provide guidance to applicants. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2024

Improving Reliability of Large Language Models for Nuclear Power Plant Diagnostics Technical Presentation

Large Language Models (LLMs) struggle out of the box when answering factually about detailed questions, especially in domains that are sparsely represented in their training data. This causes hallucinations and reduces reliability making it difficult for them to be used in practice. This work shows that using RAG techniques can improve factual accuracy and reliability, allowing for the application of LLMs in specialized areas, even when those areas that aren’t extensively covered in their initial training.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2024

Evaluating the Use of Foundational Chemical Language Models in Multimodal Graph Fusion

Rapid and accurate prediction of the physicochemical properties of molecules given their structures remains a key challenge in cheminformatics. Machine learning approaches offer high-throughput options, but the optimality of inductive biases and data representations are up for debate. For example, BERT-based masked language models (MLMs) can be trained in a self-supervised way on hundreds of millions to billions of readily available SMILES strings. Another option is graph neural networks (GNNs), which can operate directly on molecular structures. Yet, generating accurate molecular geometry is computationally expensive, leading to a relative scarcity in data compared to SMILES strings. It is attractive to combine these two paradigms by pre-training an LM on a large corpus of SMILES strings and embedding these representation into a geometric graph neural network. Despite the promise of such an approach, and contrary to previous studies, we find mixed results with the combination of the LMs and GNNs on several molecule datasets. In particular, we found evidence for improvement on the FreeSolv and QM7 benchmarks, but degraded performance on the ESOL, LIPO and QM9 datasets compared to a GNN baseline.

Francel, Collin [University of Alabama]↗