Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “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.

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

At least 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
NASA NTRS2006

Developing Formal Correctness Properties from Natural Language Requirements

This viewgraph presentation reviews the rationale of the program to transform natural language specifications into formal notation.Specifically, automate generation of Linear Temporal Logic (LTL)correctness properties from natural language temporal specifications. There are several reasons for this approach (1) Model-based techniques becoming more widely accepted, (2) Analytical verification techniques (e.g., model checking, theorem proving) significantly more effective at detecting types of specification design errors (e.g., race conditions, deadlock) than manual inspection, (3) Many requirements still written in natural language, which results in a high learning curve for specification languages, associated tools and increased schedule and budget pressure on projects reduce training opportunities for engineers, and (4) Formulation of correctness properties for system models can be a difficult problem. This has relevance to NASA in that it would simplify development of formal correctness properties, lead to more widespread use of model-based specification, design techniques, assist in earlier identification of defects and reduce residual defect content for space mission software systems. The presentation also discusses: potential applications, accomplishments and/or technological transfer potential and the next steps.

requirements engineering↗
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Simultaneously, these reports and corresponding repositories are often only manually analyzed and queried by users via out-of-date search engines.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 NTRS2023

A Common Trajectory Language for New Airspace Domains

Revolutionary new aviation services are currently in development, including small package delivery and short-range urban passenger transportation. These new services need a language to represent and deconflict trajectories, and a common language will simplify coordination between the new airspace domains as well as traditional airspace. A Trajectory Specification Language (TSL) was previously proposed for traditional air traffic, and it can also serve as a common language for the new aviation domains and services. The TSL specifies a reference trajectory in 4D space along with spatial tolerances that determine a bounding volume at any given time in flight. The tolerances are defined in terms of the route-oriented cross-track, along-track, and vertical axes, and they are allowed to vary with distance along the route. This bounding model can guarantee safe separation between flights as long as they are in conformance with their assigned trajectories. The advantages of this model over the previously proposed Operational Intent Volumes (OIVs) in terms of airspace usage efficiency are explained.

air traffic control, aircraft trajectory, language↗
DOE OSTI2017

Identifying Effective Signals to Predict Deleted and Suspended Accounts on Twitter across Languages

Social networks have an ephemerality to them where accounts and messages are constantly being edited, deleted, or marked as private. This continuous change comes from concerns around privacy, a potential desire for deception, and spam-like behavior. In this study we analyze multiple large datasets of thousands of active and deleted Twitter accounts to produce a series of predictive features for the removal or shutdown of an account. We have selected these accounts from speakers of three languages -- Russian, Spanish, and English to evaluate if speakers of various languages behave differently with regards to deleting accounts. We find that unlike previously used profile and network features, the discourse of deleted vs. active accounts forms the basis for highly accurate account deletion prediction. More precisely, we observed that the presence of a certain set of terms in user tweets leads to a higher likelihood for that user's account deletion. We show that the predictive power of profile, language, affect, and network features is not consistent across speakers of the three evaluated languages.

account deletion prediction↗
DOE OSTI2017

Identifying Effective Signals to Predict Deleted and Suspended Accounts on Twitter across Languages

Social networks have an ephemerality to them where accounts and messages are constantly being edited, deleted, or marked as private. This continuous change comes from concerns around privacy, a potential desire for deception, and spam-like behavior. In this study we analyze multiple large datasets of thousands of active and deleted Twitter accounts to produce a series of predictive features for the removal or shutdown of an account. We have selected these accounts from speakers of three languages -- Russian, Spanish, and English to evaluate if speakers of various languages behave differently with regards to deleting accounts. We find that unlike previously used profile and network features, the discourse of deleted vs. active accounts forms the basis for highly accurate account deletion prediction. More precisely, we observed that the presence of a certain set of terms in user tweets leads to a higher likelihood for that user's account deletion. We show that the predictive power of profile, language, affect, and network features is not consistent across speakers of the three evaluated languages.

social media, machine learning, natural language p↗
DOE OSTI2026

SmileyLlama: modifying large language models for directed chemical space exploration

Here we show that large language models (LLMs) can be transformed via supervised fine-tuning of engineered prompts into SmileyLlama for exploring the chemical space of drug molecules. We benchmark SmileyLlama against pretrained LLMs and chemical language models trained from scratch for generating valid and novel drug-like molecules, and use direct preference optimization to both improve SmileyLlama’s adherence to a prompt and as part of the iMiner reinforcement learning framework to predict molecules with optimized three-dimensional conformations and high binding affinity to drug targets. By training an LLM to speak directly as a chemical language model, while retaining most of its natural language capabilities, we show that SmileyLlama can reliably generate molecules with user-specified properties rather than acting only as a chatbot with knowledge of chemistry or as a virtual assistant. While SmileyLlama is geared toward drug discovery, the supervised fine-tuning/direct preference optimization/LLM framework can be extended to other chemical, biological and materials applications.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Decoding substance use disorder severity from clinical notes using a large language model

Substance use disorder (SUD) poses a major concern due to its detrimental effects on health and society. SUD identification and treatment depend on a variety of factors such as severity, co-determinants (e.g., withdrawal symptoms), and social determinants of health. Existing diagnostic coding systems used by insurance providers, like the International Classification of Diseases (ICD-10), lack granularity for certain diagnoses, but American clinicians will add this granularity (as that found within the Diagnostic and Statistical Manual of Mental Disorders classification or DSM-5) as supplemental unstructured text in clinical notes. Traditional natural language processing (NLP) methods face limitations in accurately parsing such diverse clinical language. Large language models (LLMs) offer promise in overcoming these challenges by adapting to diverse language patterns. This study investigates the application of LLMs for extracting severity-related information for various SUD diagnoses from clinical notes. We propose a workflow employing zero-shot learning of LLMs with carefully crafted prompts and post-processing techniques. Through experimentation with Flan-T5, an open-source LLM, we demonstrate its superior recall compared to the rule-based approach. Focusing on 11 categories of SUD diagnoses, we show the effectiveness of LLMs in extracting severity information, contributing to improved risk assessment and treatment planning for SUD patients.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2012

Domain-Specific Languages for Composing Signature Discovery Workflows

Domain-agnostic signature discovery entails investigation across multiple scientific disciplines. The breadth and cross-disciplinary nature of this work requires that existing executables be integrated with new capabilities into workflows, representing a wide range of user tasks. An algorithm may be written in multiple programming languages for various hardware platforms, and so workflow composition requires integrating executables from any number of remote hosts. This raises an engineering issue on how to generate web service wrappers for these heterogeneous executables and to compose them into a scientific workflow environment (e.g., Taverna). In this paper, we introduce two simple Domain-Specific Languages (DSLs) to automate these processes. Our Service Description Language (SDL) describes key elements of a signature discovery service and automatically generates its implementation code. The Workflow Description Language (WDL) describes the pipeline of services and generates deployable artifacts for the Taverna workflow management system. We demonstrate our approach with a real-world workflow composed of services wrapping remote executables.

Jacob, Ferosh↗
DOE OSTI2018

FLPR: The Fortran Language Program Remodeling system

The Fortran Language Program Remodeling system (FLPR) is a C++ library designed to manipulate Fortran language source code files. A client can use FLPR to rapidly develop utilities that perform application-specific source code transformations. Examples of transformations are varied, ranging from simple tasks such as reformatting source code, to complex transformations that implement application-specific extensions to the Fortran language. Two unique features of FLPR are that it allows the client to extend the language that it recognizes, and that it allows the client to manipulate all of the text in a source code file, including formatting and comments.

henning, Robert↗
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 OSTI2021

An Introduction to Word Embeddings and Language Models

Language models have advanced at a phenomenal pace over the past decade. This document provides a short introduction to terminology, word embeddings (aka low-dimensional representations), and popular large-scale language models (LMs). Word embeddings are used to represent words as numerical vectors and are context-independent, meaning a word can only have a single representation (e.g., club can only be club sandwich, not golf club ). Language models can determine the probability of a given sequence of words occurring in a sentence and can provide context to distinguish between words and phrases that sound similar. LMs are context-dependent (e.g., club can be club sandwich or golf club ) and largely fall in two main classes – autoregressive and autoencoding models. Autoregressive models are pretrained on the classic language modeling task: guess the next token having read all the previous ones. Those models can be fine-tuned and achieve great results on many tasks, the most natural application is text generation. A typical example of such models is GPT, but others include GPT-2, GPT-3, CTLR, TRANSFORMER-XL, REFORMER, XLNET. Autoencoding models are pretrained by corrupting the input tokens in some way and trying to reconstruct the original sentence. They can be fine-tuned and achieve great results on many tasks such as text generation, but their most natural application is sentence classification or token classification. A typical example of such models is BERT, but others include ROBERTA, ALBERT, XML, XML-ROBERTA, FLAUBERT AND LONGFORMER.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Predictive Indicators of the Performance of Large Language Models

In several mission contexts, it is desirable to estimate the performance of large language models (LLMs) on tasks that we cannot run directly. In light of published “scaling laws” our hypothesis is that some tasks should be consistently more challenging than others based on characteristics of the task. The goal of this project was to begin quantifying how much information about LLM performance can be gained from the features of a model and a task. Two of our statistical models struggled to converge. Pass/fail test results may provide limited information for inference beyond model quality and task difficulty, but we see no evidence at this time for significant feature interaction effect sizes, arguing for simple models. Future work extending the models to capitalize on perplexity of ground truth answers is suggested. This project also introduces “Depth of Knowledge Variant Testing” as a strategy for more finely assessing language models on open domain question and answer tasks. We developed sets of questions that ask a language model to produce similar information while demonstrating increasing depth of knowledge, and also relabeled existing Q&A test questions with their depth of knowledge. Our results suggest further consideration of Bloom’s taxonomy and further refinement of prompts to properly elicit information at varying depths. In the course of this work, we set up a basic infrastructure for standardizing tasks and testing many language models on these tasks. In addition to testing the predictive quality of model features and performance across test suites, with this project we have introduced two new task features to contextualize each test question: the Dewey Classification main category of information covered, and the Bloom’s taxonomy level that corresponds to the depth of knowledge probed by the question. Splits across these and other features produced over five hundred task subtypes with distinct feature vectors, which we tested on half a dozen models.

97 MATHEMATICS AND COMPUTING↗
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↗
NASA NTRS1971

On a programming language for graph algorithms

An algorithmic language, GRAAL, is presented for describing and implementing graph algorithms of the type primarily arising in applications. The language is based on a set algebraic model of graph theory which defines the graph structure in terms of morphisms between certain set algebraic structures over the node set and arc set. GRAAL is modular in the sense that the user specifies which of these mappings are available with any graph. This allows flexibility in the selection of the storage representation for different graph structures. In line with its set theoretic foundation, the language introduces sets as a basic data type and provides for the efficient execution of all set and graph operators. At present, GRAAL is defined as an extension of ALGOL 60 (revised) and its formal description is given as a supplement to the syntactic and semantic definition of ALGOL. Several typical graph algorithms are written in GRAAL to illustrate various features of the language and to show its applicability.

Rheinboldt, W. C.↗
NASA NTRS1972

Flight program language requirements. Volume 3: Appendices

Government-sponsored study and development efforts were directed toward design and implementation of high level programming languages suitable for future aerospace applications. The study centered around an evaluation of the four most pertinent existing aerospace languages. Evaluation criteria were established, and selected kernels from the current Saturn 5 and Skylab flight programs were used as benchmark problems for sample coding. An independent review of the language specifications incorporated anticipated future programming requirements into the evaluation. A set of language requirements was synthesized from these activities.

Source record↗
NASA NTRS1973

Ground Operations Aerospace Language (GOAL)

GOAL, is a test engineer oriented language designed to be used to standardize procedure terminology and as the test programming language to be used for ground checkout operations in a space vehicle launch environment. The material presented concerning GOAL includes: (1) a historical review, (2) development objectives and requirements, (3) language scope and format, and (4) language capabilities.

Source record↗
NASA NTRS1973

Ground Operations Aerospace Language (GOAL). Volume 3: Data bank

The GOAL (Ground Operations Aerospace Language) test programming language was developed for use in ground checkout operations in a space vehicle launch environment. To insure compatibility with a maximum number of applications, a systematic and error-free method of referencing command/response (analog and digital) hardware measurements is a principle feature of the language. Central to the concept of requiring the test language to be independent of launch complex equipment and terminology is that of addressing measurements via symbolic names that have meaning directly in the hardware units being tested. To form the link from test program through test system interfaces to the units being tested the concept of a data bank has been introduced. The data bank is actually a large cross-reference table that provides pertinent hardware data such as interface unit addresses, data bus routings, or any other system values required to locate and access measurements.

Source record↗