SEARCH · Engineering Papers

Results for “Structured Natural Language”

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.

SourceResearch connectionFrom yearThrough year

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

At least 109 records · Page 6

All sources NASA NTRS DOE OSTI

DOE OSTI2021

Supervised extraction of near-complete genomes from metagenomic samples: A new service in PATRIC

Large amounts of metagenomically-derived data are submitted to PATRIC for analysis. In the future, we expect even more jobs submitted to PATRIC will use metagenomic data. One in-demand use case is the extraction of near-complete draft genomes from assembled contigs of metagenomic origin. The PATRIC metagenome binning service utilizes the PATRIC database to furnish a large, diverse set of reference genomes. We provide a new service for supervised extraction and annotation of high-quality, near-complete genomes from metagenomically-derived contigs. Reference genomes are assigned to putative draft genome bins based on the presence of single-copy universal marker roles in the sample, and contigs are sorted into these bins by their similarity to reference genomes in PATRIC. Each set of binned contigs represents a draft genome that will be annotated by RASTtk in PATRIC. A structured-language binning report is provided containing quality measurements and taxonomic information about the contig bins. The PATRIC metagenome binning service emphasizes extraction of high-quality genomes for downstream analysis using other PATRIC tools and services. Due to its supervised nature, the binning service is not appropriate for mining novel or extremely low-coverage genomes from metagenomic samples.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2024

Root Cause Correlation Analysis of Software Failures via Orthogonal Defect Classification and Natural Language Processing

Systems theoretic process analysis (STPA) is becoming an increasingly popular technique to assess how complex digital software systems can fail. Rather than defining failures by their observable failure events, which may be sparse especially for safety rated nuclear digital instrumentation and control systems (DI&C), failures are defined as postulated unsafe actions under specific contextual conditions. This permits a top-down analysis of system hazards and identifies whether imposed constraints and requirements can sufficiently address undesirable hazards. However, STPA is a qualitative approach at identifying inadequacies in the development process and cannot currently be used to quantify unsafe action likelihoods for probabilistic risk assessment. Therefore, in this work, we examine the root causes of software failure and explore whether a consistent correlation can be linked to specific unsafe action classes. We implement Lbl2Vec, an unsupervised document classification and retrieval algorithm, on a database of 4,096 software defect reports acquired from various open-source software systems. By analyzing sentence structure, embedded labels, and word vectors, we show that certain defect types positively correlate to specific unsafe action classes over others. The correlations developed can be used to estimate the failure probability of safety intended DI&C systems which provides a licensing basis for nuclear plant modernization efforts.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗

NASA NTRS1986

A study of the very high order natural user language (with AI capabilities) for the NASA space station common module

The requirements are identified for a very high order natural language to be used by crew members on board the Space Station. The hardware facilities, databases, realtime processes, and software support are discussed. The operations and capabilities that will be required in both normal (routine) and abnormal (nonroutine) situations are evaluated. A structure and syntax for an interface (front-end) language to satisfy the above requirements are recommended.

Gill, E. N.↗

DOE OSTI2024

Root Cause Correlation Analysis of Software Failures via Orthogonal Defect Classification and Natural Language Processing

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2018

daft [SWR-17-53]

Daft is a Haskell library that implements the key constructs of relational algebra via static structural typing. Its DataCube typeclass supports selection, projection, aggregation, disaggregation, natural joins, semijoins, and antijoins. Instances of DataCube include both map- and function-based representations. An additional abstract data type provides Vinyl-style, keyed relational tables for which an embedded domain-specific language compactly represents relational operations. Utility types and functions support serialization to tab-separated-value data files, JSON arrays, MongoDB documents, and PostgreSQL tables, including automatic detection and verification of the schema for the input data.

Bush, BrianW.↗

DOE OSTI2022

Pairwise connected tensor network representation of path integrals

It has been recently shown how the tensorial nature of real-time path integrals (PIs) involving the Feynman-Vernon influence functional can be utilized with matrix product states, taking advantage of the finite length of the bath-induced memory. Tensor networks (TNs) promise to provide a unified language to express the structure of a PI. A generalized TN specifically incorporating the pairwise interaction structure of the influence functional and its invariance with respect to the average forward-backward position or the sojourn value in the form of the blip representation is derived and implemented. This pairwise connected TNPI (PC-TNPI) is illustrated through applications to typical spin-boson problems and explorations of the differences caused by the exact form of the spectral density. The storage and performance scalings are reported, showing the compactness of the representation and the efficiency of the contraction process. Finally, taking advantage of the compressed representation, the viability of using PC-TNPI for simulating multistate problems is demonstrated. The PC-TNPI structure can be shown to yield other TN algorithms currently in use. Consequently, it should be possible to use it as a starting point for deriving other optimized procedures.

36 MATERIALS SCIENCE↗

NASA NTRS2004

The Generalization of Mutual Information as the Information between a Set of Variables: The Information Correlation Function Hierarchy and the Information Structure of Multi-Agent Systems

The topic of this paper is a hierarchy of information-like functions, here named the information correlation functions, where each function of the hierarchy may be thought of as the information between the variables it depends upon. The information correlation functions are particularly suited to the description of the emergence of complex behaviors due to many- body or many-agent processes. They are particularly well suited to the quantification of the decomposition of the information carried among a set of variables or agents, and its subsets. In more graphical language, they provide the information theoretic basis for understanding the synergistic and non-synergistic components of a system, and as such should serve as a forceful toolkit for the analysis of the complexity structure of complex many agent systems. The information correlation functions are the natural generalization to an arbitrary number of sets of variables of the sequence starting with the entropy function (one set of variables) and the mutual information function (two sets). We start by describing the traditional measures of information (entropy) and mutual information.

Wolf, David R.↗

DOE OSTI2025

Finch: Toxicity Dose Response Curve Prediction of Chemical Compounds and Mixtures

A paradigm shift in chemical risk assessment is emphasizing mixture testing over single compound analysis, eliminating animal testing, and adopting advanced modeling approaches to understand mixture activity profiles. However, existing computational models largely focus on single chemicals, with few effective solutions for modeling complex mixtures that account for synergistic or antagonistic effects and multiple Modes of Action (MoA). Conventional methods like concentration addition (CA) and independent action (IA) are insufficient for this task as they are designed for simplistic interactions and struggle to account for the dynamic and multifaceted nature of chemical mixtures, such as overlapping MoA and non-linear interactions. Finch offers a novel approach utilizing deep learning (DL) embeddings and multi-task quantitative structure-activity relationship (QSAR) models to improve chemical exposure prediction. By leveraging molecular descriptors, physiochemical properties, and large language model (LLM) embeddings from SMILES inputs, Finch preserves critical information in a latent space thereby enhancing predictive accuracy. The multi-task learning aspect of Finch is highly advantageous, as it simultaneously optimizes multiple loss functions, leveraging all available data across tasks to develop generalized representations that effectively capture complex ingredient interactions within mixtures.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2025

ON THE EFFECTIVENESS OF LLMS IN UNIT TEST GENERATION FOR STRUCTURED TEXT PROGRAMS

The reliability of industrial automation systems heavily depends on the correctness of Programmable Logic Controller (PLC) programs, which are often written in Structured Text (ST). While Large Language Models (LLMs) have shown promise in automating test generation for mainstream programming languages, their effectiveness for the syntactically strict ST language remains underexplored. This thesis presents a systematic empirical evaluation of three state-of-the-art LLMs—GPT-4o, Gemini 2.5 Pro, and Claude Sonnet 4.5—for generating ST unit tests. We examine three prompting strategies: Natural Language (NL), Code Language (CL), and Chain-of-Thought (CoT), across a curated set of 11 ST function blocks. The quality of the generated tests is assessed using Compilation Success Rate (CSR), Statement Coverage (SC), and Branch Coverage (BC). In the zero-shot setting, Claude Sonnet 4.5 achieves the highest CSR, while Gemini 2.5 Pro consistently delivers the best statement and branch coverage, particularly under CL prompts. By incorporating a one-shot CL prompt, all models exhibit substantial improvements—most notably GPT-4o, whose CSR increases from 45.45% to 90.91%, with substantial gains in both SC and BC. To further contextualize these findings, we compare GPT-4o’s one-shot results with PLCAutoTester, a state-ofthe- art ST unit test generation tool, on an additional benchmark dataset. While LLMgenerated tests approach competitive coverage levels, PLCAutoTester maintains significantly higher and more stable coverage across programs. This study provides the first comprehensive benchmark of modern LLMs for ST unit testing, highlighting their strengths, limitations, and improvements through one-shot prompting, and positioning their performance relative to specialized automated testing tools in industrial automation.

42 ENGINEERING↗

DOE OSTI2026

From natural language to control signals: a conceptual framework for semantic channel finding in complex experimental infrastructure

Modern experimental platforms such as particle accelerators, fusion devices, telescopes, and industrial process control systems expose tens to hundreds of thousands of control and diagnostic channels, accumulated over decades of hardware evolution. Operators and AI systems alike depend on informal expert knowledge, inconsistent naming conventions, and scattered documentation to locate the signals required for monitoring, troubleshooting, and automated control, creating a persistent bottleneck for reliability, scalability, and emerging language-model-driven interfaces. We formalize semantic channel finding, the task of mapping natural-language intent to concrete control-system signals, as a general problem in complex experimental infrastructure, and introduce a four-paradigm conceptual framework to guide architecture selection based on facility-specific data regimes. The paradigms span (i) direct in-context lookup over small, curated channel dictionaries, (ii) constrained hierarchical navigation through structured trees, (iii) interactive agent exploration using iterative reasoning and tool-based database queries, and (iv) ontology-grounded semantic search that decouples channel meaning from facility-specific naming conventions. We demonstrate the practical feasibility of each paradigm through proof-of-concept implementations at four operational facilities spanning two orders of magnitude in scale: from compact free-electron lasers to large synchrotron light sources, operating under diverse control-system architectures ranging from clean hierarchical naming schemes to legacy environments with decades of heterogeneous conventions. Where evaluated against expert-curated operational queries, these instantiations achieve 90%–97% accuracy, validating the framework’s applicability across real-world deployment scenarios. To accelerate adoption across the broader scientific and industrial control-system community, we release open-source, plug-and-play implementations of all three interactive paradigms-direct lookup, hierarchical navigation, and middle-layer exploration-within the Osprey framework, together with tools for channel database generation, interactive testing, and minimal-configuration deployment. This work establishes semantic channel finding as a foundational capability for human-centric and agentic AI interfaces at large-scale facilities, providing both a systematic framework for architecture design and practical resources to enable adoption without building custom infrastructure from scratch.

channel finding↗

NASA NTRS1997

Querying Semi-Structured Data

The amount of data of all kinds available electronically has increased dramatically in recent years. The data resides in different forms, ranging from unstructured data in the systems to highly structured in relational database systems. Data is accessible through a variety of interfaces including Web browsers, database query languages, application-specic interfaces, or data exchange formats. Some of this data is raw data, e.g., images or sound. Some of it has structure even if the structure is often implicit, and not as rigid or regular as that found in standard database systems. Sometimes the structure exists but has to be extracted from the data. Sometimes also it exists but we prefer to ignore it for certain purposes such as browsing. We call here semi-structured data this data that is (from a particular viewpoint) neither raw data nor strictly typed, i.e., not table-oriented as in a relational model or sorted-graph as in object databases. As will seen later when the notion of semi-structured data is more precisely de ned, the need for semi-structured data arises naturally in the context of data integration, even when the data sources are themselves well-structured. Although data integration is an old topic, the need to integrate a wider variety of data- formats (e.g., SGML or ASN.1 data) and data found on the Web has brought the topic of semi-structured data to the forefront of research. The main purpose of the paper is to isolate the essential aspects of semi- structured data. We also survey some proposals of models and query languages for semi-structured data. In particular, we consider recent works at Stanford U. and U. Penn on semi-structured data. In both cases, the motivation is found in the integration of heterogeneous data.

DATA MANAGEMENT↗

DOE OSTI2018

SynthNotes: A Generator Framework for High-volume, High-fidelity Synthetic Mental Health Notes

One of the key, emerging challenges that connects the "Big Data" and the AI domain is the availability of sufficient volumes of training data for AI/Machine Learning tasks. SynthNotes is a framework for generating standards-compliant, realistic mental health progress report notes at the very large, population-level scale, and in a strict privacy-preserving manner. Our framework, inspired by the needs to explore, evaluate, and train computational methods for the emerging mental health crisis in the US, is useful for benchmarking, optimization, and training of biomedical natural language processing, information extraction, and machine learning systems intended to operate at "Big Data" scale (billions of notes). The free text notes generated by SynthNotes are based on the literature and public statistical models allowing for realistic, natural language representation of a patient, and his or her mental health characteristics. Additionally, SynthNotes can partially simulate stylistic, grammatical, and expressive characteristics of a licensed mental health professional. SynthNotes is modular and flexible, allowing for representation of variety of conditions, incorporation of alternative foundational models, and parametrization of the variability of the structure, content, and size of the synthetically generated corpus. In this paper, we report on the initial use and performance characteristics of our SynthNotes framework and on the ongoing work for inclusion of content planning and deep learning-based generative methods trained on real data.

Begoli, Edmon↗

NASA NTRS1993

NELS 2.0 - A general system for enterprise wide information management

NELS, the NASA Electronic Library System, is an information management tool for creating distributed repositories of documents, drawings, and code for use and reuse by the aerospace community. The NELS retrieval engine can load metadata and source files of full text objects, perform natural language queries to retrieve ranked objects, and create links to connect user interfaces. For flexibility, the NELS architecture has layered interfaces between the application program and the stored library information. The session manager provides the interface functions for development of NELS applications. The data manager is an interface between session manager and the structured data system. The center of the structured data system is the Wide Area Information Server. This system architecture provides access to information across heterogeneous platforms in a distributed environment. There are presently three user interfaces that connect to the NELS engine; an X-Windows interface, and ASCII interface and the Spatial Data Management System. This paper describes the design and operation of NELS as an information management tool and repository.

Smith, Stephanie L.↗

DOE OSTI2018

Integrating Natural Language Processing and Machine Learning Algorithms to Categorize Oncologic Response in Radiology Reports

A significant volume of medical data remains unstructured. Natural language processing (NLP) and machine learning (ML) techniques have shown to successfully extract insights from radiology reports. However, the codependent effects of NLP and ML in this context have not been well-studied. Between April 1, 2015 and November 1, 2016, 9418 cross-sectional abdomen/pelvis CT and MR examinations containing our internal structured reporting element for cancer were separated into four categories: Progression, Stable Disease, Improvement, or No Cancer. We combined each of three NLP techniques with five ML algorithms to predict the assigned label using the unstructured report text and compared the performance of each combination. The three NLP algorithms included term frequency-inverse document frequency (TF-IDF), term frequency weighting (TF), and 16-bit feature hashing. The ML algorithms included logistic regression (LR), random decision forest (RDF), one-vs-all support vector machine (SVM), one-vs-all Bayes point machine (BPM), and fully connected neural network (NN). The best-performing NLP model consisted of tokenized unigrams and bigrams with TF-IDF. Increasing N-gram length yielded little to no added benefit for most ML algorithms. With all parameters optimized, SVM had the best performance on the test dataset, with 90.6 average accuracy and F score of 0.813. The interplay between ML and NLP algorithms and their effect on interpretation accuracy is complex. The best accuracy is achieved when both algorithms are optimized concurrently.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

NASA NTRS2005

Formal Safety Certification of Aerospace Software

In principle, formal methods offer many advantages for aerospace software development: they can help to achieve ultra-high reliability, and they can be used to provide evidence of the reliability claims which can then be subjected to external scrutiny. However, despite years of research and many advances in the underlying formalisms of specification, semantics, and logic, formal methods are not much used in practice. In our opinion this is related to three major shortcomings. First, the application of formal methods is still expensive because they are labor- and knowledge-intensive. Second, they are difficult to scale up to complex systems because they are based on deep mathematical insights about the behavior of the systems (t.e., they rely on the "heroic proof"). Third, the proofs can be difficult to interpret, and typically stand in isolation from the original code. In this paper, we describe a tool for formally demonstrating safety-relevant aspects of aerospace software, which largely circumvents these problems. We focus on safely properties because it has been observed that safety violations such as out-of-bounds memory accesses or use of uninitialized variables constitute the majority of the errors found in the aerospace domain. In our approach, safety means that the program will not violate a set of rules that can range for the simple memory access rules to high-level flight rules. These different safety properties are formalized as different safety policies in Hoare logic, which are then used by a verification condition generator along with the code and logical annotations in order to derive formal safety conditions; these are then proven using an automated theorem prover. Our certification system is currently integrated into a model-based code generation toolset that generates the annotations together with the code. However, this automated formal certification technology is not exclusively constrained to our code generator and could, in principle, also be integrated with other code generators such as RealTime Workshop or even applied to legacy code. Our approach circumvents the historical problems with formal methods by increasing the degree of automation on all levels. The restriction to safety policies (as opposed to arbitrary functional behavior) results in simpler proof problems that can generally be solved by fully automatic theorem proves. An automated linking mechanism between the safety conditions and the code provides some of the traceability mandated by process standards such as DO-178B. An automated explanation mechanism uses semantic markup added by the verification condition generator to produce natural-language explanations of the safety conditions and thus supports their interpretation in relation to the code. It shows an automatically generated certification browser that lets users inspect the (generated) code along with the safety conditions (including textual explanations), and uses hyperlinks to automate tracing between the two levels. Here, the explanations reflect the logical structure of the safety obligation but the mechanism can in principle be customized using different sets of domain concepts. The interface also provides some limited control over the certification process itself. Our long-term goal is a seamless integration of certification, code generation, and manual coding that results in a "certified pipeline" in which specifications are automatically transformed into executable code, together with the supporting artifacts necessary for achieving and demonstrating the high level of assurance needed in the aerospace domain.

Denney, Ewen↗

DOE OSTI2025

Extraction and Analysis of Time Series Data from Building Automation Systems Using Large Language Models

Semantic schemas like Haystack 4, Brick and ASHRAE standard 223 enable the structured, standardized, and machine-readable representation of building data, facilitating interoperability, data integration, and advanced analytics. However, extracting information from these models requires specialized expertise in SPARQL and other programming languages, skills that are not commonly found among building professionals. Recent advancements in Large Language Models (LLMs), such as ChatGPT, enable the construction of queries using natural language, making it easier for individuals to interact with these systems in a manner that resembles everyday speech. However, these methods have not yet been tested on building semantic ontologies. This paper introduces a novel workflow and tool for enabling users to ask questions about a specific building's data, using natural language and receive answers automatically generated by GPT-4o. Our approach integrates semantic ontologies with advanced LLM capabilities to automate three critical steps: (1) generating SPARQL queries to retrieve time series references from ontological models, (2) extracting the corresponding time series data from the Building Automation System, and (3) performing computations and visualizations tailored to the user's query. The proposed method simplifies access to BAS data, allowing both domain experts and non-specialists to conduct sophisticated analyses without needing extensive technical knowledge of semantic web technologies. By demonstrating this pipeline, we facilitate more accessible and scalable data-driven decision-making in building operations and management.

Mulayim, Ozan Baris↗

DOE OSTI2025

Extraction and Analysis of Time Series Data from Building Automation Systems Using Large Language Models

Mulayim, Ozan Baris↗

NASA NTRS1996

Constraints in Genetic Programming

Genetic programming refers to a class of genetic algorithms utilizing generic representation in the form of program trees. For a particular application, one needs to provide the set of functions, whose compositions determine the space of program structures being evolved, and the set of terminals, which determine the space of specific instances of those programs. The algorithm searches the space for the best program for a given problem, applying evolutionary mechanisms borrowed from nature. Genetic algorithms have shown great capabilities in approximately solving optimization problems which could not be approximated or solved with other methods. Genetic programming extends their capabilities to deal with a broader variety of problems. However, it also extends the size of the search space, which often becomes too large to be effectively searched even by evolutionary methods. Therefore, our objective is to utilize problem constraints, if such can be identified, to restrict this space. In this publication, we propose a generic constraint specification language, powerful enough for a broad class of problem constraints. This language has two elements -- one reduces only the number of program instances, the other reduces both the space of program structures as well as their instances. With this language, we define the minimal set of complete constraints, and a set of operators guaranteeing offspring validity from valid parents. We also show that these operators are not less efficient than the standard genetic programming operators if one preprocesses the constraints - the necessary mechanisms are identified.

Janikow, Cezary Z.↗