Results for “Common Language” — Page 6

NASA NTRS1994

Automating Testbed Documentation and Database Access Using World Wide Web (WWW) Tools

A method for providing uniform transparent access to disparate distributed information systems was demonstrated. A prototype testing interface was developed to access documentation and information using publicly available hypermedia tools. The prototype gives testers a uniform, platform-independent user interface to on-line documentation, user manuals, and mission-specific test and operations data. Mosaic was the common user interface, and HTML (Hypertext Markup Language) provided hypertext capability.

documentation↗

NASA NTRSDate not supplied

Risks of Increased Earth Independence

As human space exploration begins to extend beyond the immediate vicinity of Earth, the ability of expertise on the ground to support operations will progressively decrease. Ground control expertise has been the primary countermeasure preventing loss of life and mission over the past sixty years and it will be gradually stripped away as expeditions reach further into space. The large, flexible and adaptive teams of experts on the ground, provide not only engineering analysis and problem-solving but also greatly increased work capacity. Monitoring of the large and fast moving stream of telemetry data is carried out around the clock by 20-30 flight controllers per shift. Analysis of that data and troubleshooting is carried out by an additional 50-100 engineers per shift. Artificial intelligence capabilities will need to be part of the solution but will not the entire solution. As progress continues to be made on intelligent systems, especially those for use in complex, dynamic environments where humans will remain a part of the activity, there is an ever increasing need to focus on how those systems will interact with the humans. Although capabilities such as natural language processing and facial recognition have become common place, even basic aspects of problem-solving, causal reasoning and generative decision-making remain well-beyond of our current capabilities. Advanced data visualization, procedure execution support, and new training approaches will be needed to close the gap between what is currently provided by experts on the ground and what the crew will need to do in increasingly autonomous ways with greater distance from Earth.

human-systems integration architecture↗

NASA NTRS1986

An evaluation of Ada for Al applications

Expert system technology seems to be the most promising type of Artificial Intelligence (AI) application for Ada. An expert system implemented with an expert system shell provides a highly structured approach that fits well with the structured approach found in Ada systems. The current commercial expert system shells use Lisp. In this highly structured situation a shell could be built that used Ada just as well. On the other hand, if it is necessary to deal with some AI problems that are not suited to expert systems, the use of Ada becomes more problematical. Ada was not designed as an AI development language, and is not suited to that. It is possible that an application developed in say, Common Lisp could be translated to Ada for actual use in a particular application, but this could be difficult. Some standard Ada packages could be developed to make such a translation easier. If the most general AI programs need to be dealt with, a Common Lisp system integrated with the Ada Environment is probably necessary. Aside from problems with language features, Ada, by itself, is not well suited to the prototyping and incremental development that is well supported by Lisp.

Wallace, David R.↗

NASA NTRS1988

Languages for artificial intelligence: Implementing a scheduler in LISP and in Ada

A prototype scheduler for space experiments originally programmed in a dialect of LISP using some of the more traditional techniques of that language, was recast using an object-oriented LISP, Common LISP with Flavors on the Symbolics. This object-structured version was in turn partially implemented in Ada. The Flavors version showed a decided improvement in both speed of execution and readability of code. The recasting into Ada involved various practical problems of implementation as well as certain challenges of reconceptualization in going from one language to the other. Advantages were realized, however, in greater clarity of the code, especially where more standard flow of control was used. This exercise raised issues about the influence of programming language on the design of flexible and sensitive programs such as schedule planners, and called attention to the importance of factors external to the languages themselves such as system embeddedness, hardware context, and programmer practice.

Hays, Dan↗

NASA NTRS2025

Detangling Safety Knowledge with Contextualism

We have contradictory intuitions about knowing that things are safe: on the one hand, we claim to have knowledge that many systems (even complex ones) are safe in ordinary language. On the other hand, when challenged by an expert, we easily admit that we do not, in fact, possess very much safety knowledge at all. This Technical Memorandum (TM) attempts to reconcile these two competing intuitions using a philosophical view called epistemic contextualism. We can use epistemic contextualism to explain the importance of safety regulations and the goal in implementing them: first, to differentiate types of disagreement and establish a common basis upon which regulators and regulatees can know that a system is safe; second, to raise ordinary consumers’ standards for safety knowledge (given adequate knowledge of the comprehensiveness of the regulation). This TM also uses the contextualist framework of relevant alternatives to elucidate types of failure possibilities and explain complications in attempts to prevent common mode failures.

language↗

NASA NTRS1984

Concepts and implementations of natural language query systems

The currently developed user language interfaces of information systems are generally intended for serious users. These interfaces commonly ignore potentially the largest user group, i.e., casual users. This project discusses the concepts and implementations of a natural query language system which satisfy the nature and information needs of casual users by allowing them to communicate with the system in the form of their native (natural) language. In addition, a framework for the development of such an interface is also introduced for the MADAM (Multics Approach to Data Access and Management) system at the University of Southwestern Louisiana.

Dominick, Wayne D.↗

NASA NTRS1985

Natural Language Query System Design for Interactive Information Storage and Retrieval Systems

The currently developed multi-level language interfaces of information systems are generally designed for experienced users. These interfaces commonly ignore the nature and needs of the largest user group, i.e., casual users. This research identifies the importance of natural language query system research within information storage and retrieval system development; addresses the topics of developing such a query system; and finally, proposes a framework for the development of natural language query systems in order to facilitate the communication between casual users and information storage and retrieval systems.

Dominick, Wayne D.↗

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 NTRS1988

Using hypermedia to develop an intelligent tutorial/diagnostic system for the Space Shuttle Main Engine Controller Lab

This is a tutorial/diagnostic system for training personnel in the use of the Space Shuttle Main Engine Controller (SSMEC) Simulation Lab. It also provides a diagnostic capable of isolating lab failures at least to the major lab component. The system was implemented using Hypercard, which is an program of hypermedia running on Apple Macintosh computers. Hypercard proved to be a viable platform for the development and use of sophisticated tutorial systems and moderately capable diagnostic systems. This tutorial/diagnostic system uses the basic Hypercard tools to provide the tutorial. The diagnostic part of the system uses a simple interpreter written in the Hypercard language (Hypertalk) to implement the backward chaining rule based logic commonly found in diagnostic systems using Prolog. Some of the advantages of Hypercard in developing this type of system include sophisticated graphics, animation, sound and voice capabilities, its ability as a hypermedia tool, and its ability to include digitized pictures. The major disadvantage is the slow execution time for evaluation of rules (due to the interpretive processing of the language). Other disadvantages include the limitation on the size of the cards, that color is not supported, that it does not support grey scale graphics, and its lack of selectable fonts for text fields.

Oreilly, Daniel↗

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 create more accurate transcripts of air traffic management conversations. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement (LOA) which is used as the evaluation case in this paper. These applications can benefit from the use of state-of-the-art Natural Language Processing (NLP) techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of transferring pre-trained large language models to the aviation domain by adapting transformer based models using aviation datasets. This paper utilized two datasets to adapt a ‘Robustly Optimized Bidirectional Encoder Representations from Transformers Approach’ (RoBERTa) model and two down-stream classification tasks to assess its performance. These datasets are all built upon Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. The first two datasets are used for the adaptation of RoBERTa to the aviation domain and were of different sizes to assess the number of documents needed to adapt to the aviation domain. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the unsupervised adaptation. The second dataset is a separate set of LOA documents with two sets of classification labels to be used for evaluation; one at the document level and one at the line level. These down-stream evaluations allowed the measurement of improvement by adapting RoBERTa. The accuracy increased by 4-6% on both tasks and the F1 score on the class of interest increased by 4-8% from the adaptation.

Air Traffic Management↗

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 create more accurate transcripts of air traffic management conversations. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement (LOA) which is used as the evaluation case in this paper. These applications can benefit from the use of state-of-the-art Natural Language Processing (NLP) techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of transferring pre-trained large language models to the aviation domain by adapting transformer based models using aviation datasets. This paper utilized two datasets to adapt a ‘Robustly Optimized Bidirectional Encoder Representations from Transformers Approach’ (RoBERTa) model and two down-stream classification tasks to assess its performance. These datasets are all built upon Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. The first two datasets are used for the adaptation of RoBERTa to the aviation domain and were of different sizes to assess the number of documents needed to adapt to the aviation domain. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the unsupervised adaptation. The second dataset is a separate set of LOA documents with two sets of classification labels to be used for evaluation; one at the document level and one at the line level. These down-stream evaluations allowed the measurement of improvement by adapting RoBERTa. The accuracy increased by 4-6% on both tasks and the F1 score on the class of interest increased by 4-8% from the adaptation.

Air Traffic Management↗

NASA NTRS1972

Thermal Network Modelling Handbook

Thermal mathematical modelling is discussed in detail. A three-fold purpose was established: (1) to acquaint the new user with the terminology and concepts used in thermal mathematical modelling, (2) to present the more experienced and occasional user with quick formulas and methods for solving everyday problems, coupled with study cases which lend insight into the relationships that exist among the various solution techniques and parameters, and (3) to begin to catalog in an orderly fashion the common formulas which may be applied to automated conversational language techniques.

Source record↗

NASA NTRS2002

On the nature and evolution of the neural bases of human language

The traditional theory equating the brain bases of language with Broca's and Wernicke's neocortical areas is wrong. Neural circuits linking activity in anatomically segregated populations of neurons in subcortical structures and the neocortex throughout the human brain regulate complex behaviors such as walking, talking, and comprehending the meaning of sentences. When we hear or read a word, neural structures involved in the perception or real-world associations of the word are activated as well as posterior cortical regions adjacent to Wernicke's area. Many areas of the neocortex and subcortical structures support the cortical-striatal-cortical circuits that confer complex syntactic ability, speech production, and a large vocabulary. However, many of these structures also form part of the neural circuits regulating other aspects of behavior. For example, the basal ganglia, which regulate motor control, are also crucial elements in the circuits that confer human linguistic ability and abstract reasoning. The cerebellum, traditionally associated with motor control, is active in motor learning. The basal ganglia are also key elements in reward-based learning. Data from studies of Broca's aphasia, Parkinson's disease, hypoxia, focal brain damage, and a genetically transmitted brain anomaly (the putative "language gene," family KE), and from comparative studies of the brains and behavior of other species, demonstrate that the basal ganglia sequence the discrete elements that constitute a complete motor act, syntactic process, or thought process. Imaging studies of intact human subjects and electrophysiologic and tracer studies of the brains and behavior of other species confirm these findings. As Dobzansky put it, "Nothing in biology makes sense except in the light of evolution" (cited in Mayr, 1982). That applies with as much force to the human brain and the neural bases of language as it does to the human foot or jaw. The converse follows: the mark of evolution on the brains of human beings and other species provides insight into the evolution of the brain bases of human language. The neural substrate that regulated motor control in the common ancestor of apes and humans most likely was modified to enhance cognitive and linguistic ability. Speech communication played a central role in this process. However, the process that ultimately resulted in the human brain may have started when our earliest hominid ancestors began to walk.

Review, Tutorial↗

NASA NTRS2005

An XML Representation for Crew Procedures

NASA ensures safe operation of complex systems through the use of formally-documented procedures, which encode the operational knowledge of the system as derived from system experts. Crew members use procedure documentation on the ground for training purposes and on-board space shuttle and space station to guide their activities. Investigators at JSC are developing a new representation for procedures that is content-based (as opposed to display-based). Instead of specifying how a procedure should look on the printed page, the content-based representation will identify the components of a procedure and (more importantly) how the components are related (e.g., how the activities within a procedure are sequenced; what resources need to be available for each activity). This approach will allow different sets of rules to be created for displaying procedures on a computer screen, on a hand-held personal digital assistant (PDA), verbally, or on a printed page, and will also allow intelligent reasoning processes to automatically interpret and use procedure definitions. During his NASA fellowship, Dr. Simpson examined how various industries represent procedures (also called business processes or workflows), in areas such as manufacturing, accounting, shipping, or customer service. A useful method for designing and evaluating workflow representation languages is by determining their ability to encode various workflow patterns, which depict abstract relationships between the components of a procedure removed from the context of a specific procedure or industry. Investigators have used this type of analysis to evaluate how well-suited existing workflow representation languages are for various industries based on the workflow patterns that commonly arise across industry-specific procedures. Based on this type of analysis, it is already clear that existing workflow representations capture discrete flow of control (i.e., when one activity should start and stop based on when other activities start and stop), but do not capture the flow of data, materials, resources or priorities. Existing workflow representation languages are also limited to representing sequences of discrete activities, and cannot encode procedures involving continuous flow of information or materials between activities.

Simpson, Richard C.↗

NASA NTRS2022

Natural Language Processing Techniques for Intelligent Knowledge Management of Safety Reports

Safety, failure, and incident reports are common artifacts across various domains, including aviation and wildfire response. These reports are often mandatory to submit, resulting in the culmination of large repositories of text-based documents. Simultaneously, these reports and corresponding repositories are often only manually analyzed and queried by users via out-of-date search engines. As a consequence, we have been developing the Manager for Intelligent Knowledge Access (MIKA) toolkit, which uses natural language processing to improve information access and reuse. In this presentation, we discuss natural language processing techniques for knowledge discovery and apply these methods to a repository of aerial wildfire mishap reports. Two methods are used for knowledge discovery: topic modeling and named-entity recognition. We use topic modeling to identify hazards and perform a trend analysis to produce a data-driven risk matrix. A custom named-entity recognition model, build from fine tuning a pre-trained language model, is used to identify failure modes, failure causes, failure effects, control processes, and recommendations to aid in failure modes and effects analysis (FMEA). Throughout the presentation, we discuss and apply natural language processing techniques to better leverage the vast amount of information contained in report repositories.

Machine learning↗

NASA NTRS2010

A Comparison and Evaluation of Real-Time Software Systems Modeling Languages

A model-driven approach to real-time software systems development enables the conceptualization of software, fostering a more thorough understanding of its often complex architecture and behavior while promoting the documentation and analysis of concerns common to real-time embedded systems such as scheduling, resource allocation, and performance. Several modeling languages have been developed to assist in the model-driven software engineering effort for real-time systems, and these languages are beginning to gain traction with practitioners throughout the aerospace industry. This paper presents a survey of several real-time software system modeling languages, namely the Architectural Analysis and Design Language (AADL), the Unified Modeling Language (UML), Systems Modeling Language (SysML), the Modeling and Analysis of Real-Time Embedded Systems (MARTE) UML profile, and the AADL for UML profile. Each language has its advantages and disadvantages, and in order to adequately describe a real-time software system's architecture, a complementary use of multiple languages is almost certainly necessary. This paper aims to explore these languages in the context of understanding the value each brings to the model-driven software engineering effort and to determine if it is feasible and practical to combine aspects of the various modeling languages to achieve more complete coverage in architectural descriptions. To this end, each language is evaluated with respect to a set of criteria such as scope, formalisms, and architectural coverage. An example is used to help illustrate the capabilities of the various languages.

Evensen, Kenneth D.↗

NASA NTRS1989

Managing Data From Signal-Propagation Experiments

Computer programs generate characteristic plots from amplitudes and phases. Software system enables minicomputer to process data on amplitudes and phases of signals received during experiments in ground-mobile/satellite radio propagation. Takes advantage of file-handling capabilities of UNIX operating system and C programming language. Interacts with user, under whose guidance programs in FORTRAN language generate plots of spectra or other curves of types commonly used to characterize signals. FORTRAN programs used to process file-handling outputs into any of several useful forms.

Kantak, A. V.↗

NASA NTRS1990

Software For Development Of Expert Systems

Modular software system helps create efficient artificial-intelligence computer programs. STAR*TOOL system: Set of high-level software tools; assists programmers in creation of efficient knowledge-based software systems. Provides language and capabilities for compilation of application programs written in Common LISP. Features modularity enabling elimination of unnecessary capabilities from final application program and achieves greater computing performance. Runs on any computer that supports Common LISP and has sufficient memory. Provides programmer with necessary software tools to build wide variety of reasoning and inference engines for such applications as planning, diagnosis and analysis, and simulation.

James, Mark L.↗