Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Natural Language Understanding”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
NASA NTRS2021

Perceive: Proactive Exploration of Risky Concept Emergence for Identifying Vulnerabilities & Exposures

National databases that collect various kinds of textual threat reports such as ASRS, CERT, and NVD manually process their reports individually. They then offer data products to disseminate the aggregate information, like newsletters, alerts or individual report searching. The goal of this research is to connect these individual reports thematically and temporally to identify emerging or recurring threats, by analyzing large collections of text, source code, collaboration and communication patterns. This capability, I argue, enables us to identify the emergence and recurrence of such themes, and the contexts in which they re-occur, facilitating faster and more capable mitigation. I propose two models to shed light on this goal: An empirical model of vulnerabilities as bugs, the commit flow model, and one of the vulnerabilities and aviation safety threats as topics, the topic flow model. I use as gold standard existing manual workflows in both domains, reflected in the existing data products by these organizations, and empirically evaluate if the automated model scan match or outperform existing manual practices.

ASRS↗
NASA NTRS2019

Understanding Machine Learning in Earth Science: A Natural Language Processing Approach

Machine learning (ML) is being increasingly utilized in Earth science research. Benefits of ML include efficiency, reduction of human error, and ability to extract hidden patterns within data. However, the mutual lack of each other’s domain knowledge by ML and Earth science stands as a barrier to timely and effective implementation. Earth science, in particular, faces challenges in generating sample data, compared to those of traditional ML problems such as face recognition or stock predictions, where data is abundant and not lacking in ground truth, which is necessary for labeling. Earth science data are more varying in formats, such as HDF5 and image resolutions, and are not standardized across instruments, even within a given Earth science discipline. Previous studies have been done to outline the specific challenges that Earth science faces with ML, while others have focused on using existing publications to mine information efficiently. Other resources such as Scikit-Learn have developed decision trees for choosing appropriate machine learning algorithms, but application within Earth science subjects becomes much more complex. For the current study, we propose a methodology and tool that aids in implementation of ML in Earth science using natural language processing (NLP). Our work comprises three main parts: (1) analyzing existing publications related to ML and Earth science, using natural language processing: (2) extracting from the publications information on ML models subjects in Earth Science: and (3) visualizing the extracted relationships as a network graph. The resulting network graph should aid the Earth science communities in applying optimal ML algorithms and guiding data preparation through visualization of similar studies. The network graph and analysis of document similarity will be the basis of our next step, which is to develop a decision tree for selecting optimal machine learning methodologies for specified Earth science applications.

Zheng, Laura↗
NASA NTRS2015

Collaborating with Autonomous Agents

With the anticipated increase of small unmanned aircraft systems (sUAS) entering into the National Airspace System, it is highly likely that vehicle operators will be teaming with fleets of small autonomous vehicles. The small vehicles may consist of sUAS, which are 55 pounds or less that typically will y at altitudes 400 feet and below, and small ground vehicles typically operating in buildings or defined small campuses. Typically, the vehicle operators are not concerned with manual control of the vehicle; instead they are concerned with the overall mission. In order for this vision of high-level mission operators working with fleets of vehicles to come to fruition, many human factors related challenges must be investigated and solved. First, the interface between the human operator and the autonomous agent must be at a level that the operator needs and the agents can understand. This paper details the natural language human factors e orts that NASA Langley's Autonomy Incubator is focusing on. In particular these e orts focus on allowing the operator to interact with the system using speech and gestures rather than a mouse and keyboard. With this ability of the system to understand both speech and gestures, operators not familiar with the vehicle dynamics will be able to easily plan, initiate, and change missions using a language familiar to them rather than having to learn and converse in the vehicle's language. This will foster better teaming between the operator and the autonomous agent which will help lower workload, increase situation awareness, and improve performance of the system as a whole.

Trujillo, Anna C.↗
NASA NTRS1984

Artificial intelligence, expert systems, computer vision, and natural language processing

An overview of artificial intelligence (AI), its core ingredients, and its applications is presented. The knowledge representation, logic, problem solving approaches, languages, and computers pertaining to AI are examined, and the state of the art in AI is reviewed. The use of AI in expert systems, computer vision, natural language processing, speech recognition and understanding, speech synthesis, problem solving, and planning is examined. Basic AI topics, including automation, search-oriented problem solving, knowledge representation, and computational logic, are discussed.

Gevarter, W. B.↗
NASA NTRSDate not supplied

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or aerial wildfire operations reports to better understand the risks present. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement. These applications can benefit from the use of state-of-the-art natural language processing techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of adaptation of NLP tools to the aviation domain by fine-tuning transformer based models using aviation data sets. In 2018, a novel language model based on neural units (also called transformers) was created and became known as “Bidirectional Encoder Representations from Transformers” or BERT. This architecture combined with large amounts of English training data and innovative semi-supervised training tasks set the standard for what would later emerge as Large Language Models. The performance of these models was further improved by hyperparameter tuning and refinement of the semi-supervised training task and resulted in “Robustly Optimized BERT Pre-training Approach through hyperparameter tuning” or RoBERTa models. These pre-trained Large Language Models proved to be useful for a wide variety of natural language processing tasks such as text classification and question answering through a process called fine-tuning. The transformer architecture with pre-trained weights served as the basis with the last few layers replaced with layers fine-tuned to perform a new task e.g., a layer that provides a label for the entire input text. This process of fine-tuning can also be used to adapt the models to new domains; e.g., BioBERT started with the pre-trained BERT model and was completed by additional fine-tuning and training on biomedical documents. Transformer-based architectures can also be used to create rich representations of text called embeddings which can serve as the input to other machine learning models. This allows simpler algorithms such as logistic regression to use context-rich representations of the text while still remaining quick to train and evaluate. In the world of aviation, there is a growing demand for natural language processing and understanding but the domain presents unique challenges. Due to the technical content (and specialized language) of most aviation documents, fine-tuning pre-trained Large Language Models to specific tasks has not met the benchmark on natural language processing tasks set by simpler models trained from scratch on the data. To address this deficiency, this paper evaluates the improvements from fine-tuning a Large Language Model on a large set of aviation documents using the original semi-supervised training tasks before performing specific natural language tasks. In fine-tuning, a domain-specific dataset is used on the original training task but with the pre-trained Large Language Model instead of starting from a random initialization. This approach allows the model to be adapted to the specific domain language without discarding the information gained from training on general English data. This paper utilized two major dataset types to train and assess the RoBERTa fine-tuning performance. The first are 7,057 Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the semi-supervised fine-tuning. The second type is the 494 document classification labels to be used for evaluation. This down-stream evaluation aims to show the performance of the fine-tuned model, better understand how much data is needed for an effective fine-tuning, and how fine-tuning can be adapted for different applications in-the domain. After semi-supervised training, evaluation begins by encoding the documents for classification using the fine-tuned RoBERTa model. Then a logistic regression classifier is trained to label the document type and compared against our ground truth labels. This currently leads to a 82.8% accuracy on 10-fold cross validation showing improvement over baseline RoBERTa which achieved 81.0%. We plan to measure the improvements on additional tasks and it is expected that these improvements will lead to more robust models that can tackle the natural language processing challenges present in aviation datasets.

ATM↗
NASA NTRS2008

From Informal Safety-Critical Requirements to Property-Driven Formal Validation

Most of the efforts in formal methods have historically been devoted to comparing a design against a set of requirements. The validation of the requirements themselves, however, has often been disregarded, and it can be considered a largely open problem, which poses several challenges. The first challenge is given by the fact that requirements are often written in natural language, and may thus contain a high degree of ambiguity. Despite the progresses in Natural Language Processing techniques, the task of understanding a set of requirements cannot be automatized, and must be carried out by domain experts, who are typically not familiar with formal languages. Furthermore, in order to retain a direct connection with the informal requirements, the formalization cannot follow standard model-based approaches. The second challenge lies in the formal validation of requirements. On one hand, it is not even clear which are the correctness criteria or the high-level properties that the requirements must fulfill. On the other hand, the expressivity of the language used in the formalization may go beyond the theoretical and/or practical capacity of state-of-the-art formal verification. In order to solve these issues, we propose a new methodology that comprises of a chain of steps, each supported by a specific tool. The main steps are the following. First, the informal requirements are split into basic fragments, which are classified into categories, and dependency and generalization relationships among them are identified. Second, the fragments are modeled using a visual language such as UML. The UML diagrams are both syntactically restricted (in order to guarantee a formal semantics), and enriched with a highly controlled natural language (to allow for modeling static and temporal constraints). Third, an automatic formal analysis phase iterates over the modeled requirements, by combining several, complementary techniques: checking consistency; verifying whether the requirements entail some desirable properties; verify whether the requirements are consistent with selected scenarios; diagnosing inconsistencies by identifying inconsistent cores; identifying vacuous requirements; constructing multiple explanations by enabling the fault-tree analysis related to particular fault models; verifying whether the specification is realizable.

Cimatti, Alessandro↗
NASA NTRSDate not supplied

Developing Natural Language Processing and Supervised Learning Techniques to Classify Mars Tasks

As NASA's Human Research Program (HRP) prepares for long-duration Mars missions, understanding astronaut tasks is crucial. This study, conducted at NASA Glenn Research Center (GRC), employed Natural Language Processing (NLP) and machine learning techniques to analyze and classify Mars tasks. A list of 1,058 Mars tasks was provided by HRP experts including binary labeling of 18 Human System Task Categories (HSTCs). We developed an NLP model using Google's BERT language model to capture the semantic and syntactic nuances of these tasks. Supervised training was initially applied to a subset of the NLP-analyzed tasks to assess the model's effectiveness in classifying the remaining tasks. Incorporating HSTC descriptions significantly enhanced the classification accuracy for 9 out of the 18 HSTCs and reduced training time. To address the issue of severe class imbalance in the HSTC data, we introduced innovative weighting and sampling techniques for data augmentation. We then fine-tune BERT to implement a pairwise relatedness scoring method, allowing us to cluster tasks based on their relatedness and similarity, getting a step closer to labeling the tasks without supervision. In this presentation we guide you through data preprocessing, deciphering key syntax components using BERT, and performing supervised classification of the Mars tasks. This work showcases the potential use of advanced NLP techniques to analyze Mars missions to be incorporated into various crew health and performance analyses.

GenAI↗
NASA NTRSDate not supplied

Let’s speak FRETish

FRET (https://github.com/NASA-SW-VnV/fret [github.com]) is a framework for the elicitation, formalization and analysis of requirements. FRET allows its user to enter requirements in a structured natural language called FRETish. Requirements written in FRETish are assigned unambiguous semantics. FRET supports its users in understanding this semantics and repairing requirements if applicable, by utilizing a variety of forms for each requirement: natural language description, formal mathematical logics, diagrams, and interactive simulation. FRET exports requirements into forms that can be used by a variety of analysis tools, including state-of-the-art model checkers and runtime monitoring tools. The talk will cover some of the theory behind the framework, present case studies from the aerospace and robotics domains, as well as current work on extending FRET for specifying requirements for software that learns.

FRET↗
NASA NTRSDate not supplied

FRET Tutorial

In this tutorial, we present the FRET tool for writing, understanding, formalizing and analyzing requirements. In practice, requirements are typically written in natural language, which is ambiguous and consequently not amenable to formal analysis. Since formal, mathematical notations are unintuitive, requirements in FRET are entered in a restricted, natural language, called FRETish with precise unambiguous meaning. This tutorial explains how requirements can be captured in FRETish and subsequently formalized in temporal logics and in the synchronous data flow language Lustre. We show, through multiple examples, how FRET assists users in understanding FRETish requirements and clarifying subtle semantic issues through English and diagrammatic explanations as well as interactive simulation. FInally, this tutorial describes how FRET can be used to perform realizability checking for identifying conflicting requirements and the connection of FRET with (1) the CoCoSim automated analysis tool for the verification of Simulink and Stateflow models, and (2) the Copilot runtime monitoring tool for the analysis of C programs.

FRET↗
NASA NTRSDate not supplied

Natural Language Processing for Extracting Rich Disease Data Aligned To Satellite Meteorological Data

Global climate change is redefining our understanding of how diseases spread. In Sri Lanka, vector-borne diseases such as dengue fever, encephalitis, and leptospirosis historically surged during the monsoon seasons when temperatures were high enough for mosquito eggs to hatch. Unfortunately, due to rising temperatures and more erratic rainfall patterns, mosquito eggs can now hatch year-round and are increasingly unpredictable, leading to an alarmingly increasing number of hospitalizations and deaths. More data is needed to adapt our response to these diseases in an increasingly warmer world. In the contemporary landscape, a wealth of disease information is available, yet accessibility remains limited due to unstructured data formats such as PDFs. Therefore, converting unstructured disease reports into structured formats is necessary for effectively leveraging data. This paper introduces a comprehensive framework for collecting unstructured disease reports and transforming them into analyzable formats. By creating separate models tailored to each data format, we can ensure accuracy compared to general models. These straightforward models enhance accessibility and empower other researchers to use our tools. The returned structured data can then be harnessed for analysis, statistical purposes, and informing evidence-based public health interventions, thus facilitating more informed decision-making in healthcare. We deploy this framework to produce geospatial data for Sri Lanka and Brazil for many different conditions and align these data with satellite environmental data, providing for the first time a structured, aligned powerful dataset for disease modeling.

Open Source Open Science↗
NASA NTRS1986

Intelligent user interface concept for space station

The space station computing system must interface with a wide variety of users, from highly skilled operations personnel to payload specialists from all over the world. The interface must accommodate a wide variety of operations from the space platform, ground control centers and from remote sites. As a result, there is a need for a robust, highly configurable and portable user interface that can accommodate the various space station missions. The concept of an intelligent user interface executive, written in Ada, that would support a number of advanced human interaction techniques, such as windowing, icons, color graphics, animation, and natural language processing is presented. The user interface would provide intelligent interaction by understanding the various user roles, the operations and mission, the current state of the environment and the current working context of the users. In addition, the intelligent user interface executive must be supported by a set of tools that would allow the executive to be easily configured and to allow rapid prototyping of proposed user dialogs. This capability would allow human engineering specialists acting in the role of dialog authors to define and validate various user scenarios. The set of tools required to support development of this intelligent human interface capability is discussed and the prototyping and validation efforts required for development of the Space Station's user interface are outlined.

Comer, Edward↗
NASA NTRS1995

A Comparison of Different HCI styles in a KBSE System

There has been a sizable amount of research about the relative merits of different styles of human-computer interfaces and information presentation. However, it has not been possible to declare a definitive winner between graphical and text-based interfaces. Each of these interface styles provides its own advantages that may be more relevant than the other depending on the domain and characteristics of the user population in which they are applied. This paper compares graphical and text-based interfaces for formal specifications in the context of the Amphion system. It focuses in those features that make the text-based interface desirable as a substitute or a complement to a graphical interface. In order to address these problems, a new, text-based interface has been developed as an alternative/complement to the existing graphical interface. The text-based interface avoids problems by representing the information about objects and their relationships in the form of natural language sentences. This representation makes it easy for novice users to better understand the specifications. By presenting the specification information organized in the form of outlines that can be selectively expanded and collapsed, the user is given a high degree of control over the information that is displayed at any given time.

Lazzeri, Santos Gerardo↗
NASA NTRS2020

Formal Requirements Elicitation with FRET

FRET is a tool for writing, understanding, formalizing and analyzing requirements. Users write requirements in an intuitive, restricted natural language, called FRETISH, with precise, unambiguous meaning. For a FRETISH requirement, FRET: 1) produces natural language and diagrammatic explanations of its exact meaning, 2) formalizes the requirement in logics, and 3) supports interactive simulation of produced logic formulas to ensure that they capture user intentions. FRET connects to analysis tools by facilitating the mapping between requirements and models/code, and by generating verification code. FRET is available open source at https://github.com/NASA-SW-VnV/fret; a video can be accessed at : https://tinyurl.com/fretForREFSQ.

Giannakopoulou, Dimitra↗
NASA NTRSDate not supplied

Capturing and Analyzing Requirements with FRET

FRET is an open source tool, developed at NASA Ames, for writing, understanding, formalizing, and analyzing requirements. In practice, requirements are typically written in natural language, which is ambiguous and consequently not amenable to formal analysis. Since formal, mathematical notations are unintuitive, requirements in FRET are entered in a restricted, natural language, called FRETish with precise unambiguous meaning. FRET helps users write FRETish requirements both by providing grammar information and examples during editing, but also through English and diagrammatic explanations to clarify subtle semantic issues. For each requirement, FRET automatically produces formalizations and supports interactive simulation of produced formalizations to ensure that they capture user intentions. Through its analysis portal, FRET connects to analysis tools by exporting verification code. Currently FRET connects to (1) the CoCoSim automated analysis tool for the verification of Simulink and Stateflow models, and (2) the Copilot runtime monitoring tool for the analysis of C programs. FRET also supports the consistency/realizability analysis of requirements for identifying conflicting requirements. In this tutorial, we introduce FRET and learn to speak and analyze FRETish through several examples.

FRET↗
NASA NTRS1997

Towards a Methodology for Identifying Program Constraints During Requirements Analysis

Requirements analysis is the activity that involves determining the needs of the customer, identifying the services that the software system should provide and understanding the constraints on the solution. The result of this activity is a natural language document, typically referred to as the requirements definition document. Some of the problems that exist in defining requirements in large scale software projects includes synthesizing knowledge from various domain experts and communicating this information across multiple levels of personnel. One approach that addresses part of this problem is called context monitoring and involves identifying the properties of and relationships between objects that the system will manipulate. This paper examines several software development methodologies, discusses the support that each provide for eliciting such information from experts and specifying the information, and suggests refinements to these methodologies.

Romo, Lilly↗
NASA NTRS1984

Understanding a technical language: A schema-based approach

Workers in many job categories tend to develop technical languages, which are restricted subjects of natural language. A better knowledge of these retrictions provides guidelines for the design of the restricted languages of interactive systems. Accordingly, a technical language used by air-traffic controllers in their communications with pilots was studied. A method of analysis is presented that allows the schemata underlying each category of messages to be identified. This schematic knowledge was implemented in programs, which assume that the goal-oriented aspect of technical languages (and particularly the restricted domain of discourse) limits the processes and the data necessary in order to understand the messages (monosemy, limited vocabulary, evocation of the schemata by some command words, absence of syntax). The programs can interpret, and translate into sequences of action, the messages emitted by the controllers.

Falzon, P.↗
NASA NTRSDate not supplied

Natural Language Processing Methods for Air Traffic Management Text and Speech Data

This presentation discusses two efforts of the NARI AI/ML Intern team during the Fall 2021 OSTEM Internship term. For Letters of Agreement (LoA), we have studied how LoAs are structured and explored the question ‘What is an LoA constraint?’ To do this, our approach is data-driven, iterative, and assisted by machine learning when available. In this presentation, we will walk through our tasks of manually scanning through documents, performing a preliminary entity labelling task, and our unsupervised analysis on LoA procedures sections. After this research phase, we define the smallest constraint unit in an LoA, and start to perform entity extraction. Looking towards constraint extraction, we are also exploring the use of a one-class support vector machine (OneClassSVM) model to identify patterns within the data. The second effort of our team this term is focused on Air Traffic Control System Command Center (ATCSCC) advisory meetings, and the subsequent advisory documents that get published from their content. These advisory documents are important to give readily accessible summaries of daily operations, so that data centers, airline officials, and other stakeholders can easily understand the context of these meetings in real time. In applying machine learning to this scenario, two natural language processing tasks are used. First is developing machine learning models to convert the meeting speech data into text. With this text, use of extractive and abstractive text summarization models are used to automatically generate preliminary versions of the advisory documents.

Natural Language Processing↗
NASA NTRS1989

Natural language processing and advanced information management

Integrating diverse information sources and application software in a principled and general manner will require a very capable advanced information management (AIM) system. In particular, such a system will need a comprehensive addressing scheme to locate the material in its docuverse. It will also need a natural language processing (NLP) system of great sophistication. It seems that the NLP system must serve three functions. First, it provides an natural language interface (NLI) for the users. Second, it serves as the core component that understands and makes use of the real-world interpretations (RWIs) contained in the docuverse. Third, it enables the reasoning specialists (RSs) to arrive at conclusions that can be transformed into procedures that will satisfy the users' requests. The best candidate for an intelligent agent that can satisfactorily make use of RSs and transform documents (TDs) appears to be an object oriented data base (OODB). OODBs have, apparently, an inherent capacity to use the large numbers of RSs and TDs that will be required by an AIM system and an inherent capacity to use them in an effective way.

Hoard, James E.↗