Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Natural Language Processing”

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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
DOE OSTI2018

RuSentiment: An Enriched Sentiment Analysis Dataset for Social Media in Russian

This paper presents RuSentiment, a new dataset for sentiment analysis of social media posts in Russian, and a new set of comprehensive annotation guidelines that are extensible to other languages. RuSentiment is currently the largest in its class for Russian, with 30,521 posts annotated with Cohen’s kappa of 0.58 (3 annotations per post). To diversify the dataset, 6,749 posts were pre-selected with an active learning-style strategy. We report baseline classification results, and release the bestperforming embeddings trained on 3.2B tokens in Russian VKontakte posts.

data collection, sentiment analysis, machine learn↗
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 OSTI2018

Multiple Document Representations from News Alerts for Automated Bio-surveillance Event Detection

Due to globalization, geographic boundaries no longer serve as effective shields for the spread of infectious diseases. In order to aid bio-surveillance analysts in disease tracking, recent research has been devoted to developing information retrieval and analysis methods utilizing the vast corpora of publicly available documents on the internet. In this work, we present methods for the automated retrieval and classification of documents related to active public health events. We demonstrate classification performance on an auto-generated corpus, using recurrent neural network, TFIDF, and Naive Bayes log count ratio document representations. By jointly modeling the title and description of a document, we achieve 97% recall and 93.3% accuracy with our best performing bio-surveillance event classification model; logistic regression on the combined output from a pair of bidirectional recurrent neural networks.

language analysis, Biosurveillance, document class↗
DOE OSTI2024

Causality Extraction from Nuclear Licensee Event Reports Using a Hybrid Framework

In this paper, we proposed a hybrid framework for causality detection and extraction in LER documents. The main contributions are summarized below. We 1) built an LER corpus with 20,129 text samples for causality analysis, 2) developed an interactive tool was developed for labeling cause-effect pairs, 3) built a deep learning-based approach for causal relation detection, and 4) built a knowledge-based cause-effect extraction approach.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2021

Models and Processes to Extract Drug-like Molecules From Natural Language Text

Researchers worldwide are seeking to repurpose existing drugs or discover new drugs to counter the disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). A promising source of candidates for such studies is molecules that have been reported in the scientific literature to be drug-like in the context of viral research. However, this literature is too large for human review and features unusual vocabularies for which existing named entity recognition (NER) models are ineffective. We report here on a project that leverages both human and artificial intelligence to detect references to such molecules in free text. We present 1) a iterative model-in-the-loop method that makes judicious use of scarce human expertise in generating training data for a NER model, and 2) the application and evaluation of this method to the problem of identifying drug-like molecules in the COVID-19 Open Research Dataset Challenge (CORD-19) corpus of 198,875 papers. We show that by repeatedly presenting human labelers only with samples for which an evolving NER model is uncertain, our human-machine hybrid pipeline requires only modest amounts of non-expert human labeling time (tens of hours to label 1778 samples) to generate an NER model with an F-1 score of 80.5%—on par with that of non-expert humans—and when applied to CORD’19, identifies 10,912 putative drug-like molecules. This enriched the computational screening team’s targets by 3,591 molecules, of which 18 ranked in the top 0.1% of all 6.6 million molecules screened for docking against the 3CLPro protein.

60 APPLIED LIFE SCIENCES↗
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↗
DOE OSTI2020

Do Programmers Prefer Predictable Expressions in Code?

Source code is a form of human communication, albeit one where the information shared between the programmers reading and writing the code is constrained by the requirement that the code executes correctly. Programming languages are more syntactically constrained than natural languages, but they are also very expressive, allowing a great many different ways to express even very simple computations. Still, code written by developers is highly predictable, and many programming tools have taken advantage of this phenomenon, relying on language model surprisal as a guiding mechanism. Additionally, while surprisal has been validated as a measure of cognitive load in natural language, its relation to human cognitive processes in code is still poorly understood. In this paper, we explore the relationship between surprisal and programmer preference at a small granularity—do programmers prefer more predictable expressions in code? Using meaning-preserving transformations, we produce equivalent alternatives to developer-written code expressions and run a corpus study on Java and Python projects. In general, language models rate the code expressions developers choose to write as more predictable than these transformed alternatives. Then, we perform two human subject studies asking participants to choose between two equivalent snippets of Java code with different surprisal scores (one original and transformed). We find that programmers do prefer more predictable variants, and that stronger language models like the transformer align more often and more consistently with these preferences.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2012

VCAT: Visual Crosswalk Analysis Tool [Slides]

VCAT is a knowledge modeling and analysis tool. It was synthesized from ideas in functional analysis, business process modeling, and complex network science. VCAT discovers synergies by analyzing natural language descriptions. Specifically, it creates visual analytic perspectives that capture intended organization structures, then overlays the serendipitous relationships that point to potential synergies within an organization or across multiple organizations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

An Overview of Natural Gas Conversion Technologies for Co-Production of Hydrogen and Value-Added Solid Carbon Products

This report was prepared in response to the U.S. Department of Energy Fuel Cell Technologies Office Congressional Appropriation language to support research on carbon-free production of hydrogen using new chemical processes that utilize natural gas to produce solid carbon and hydrogen. The U.S. produces 9-10 million tons of hydrogen annually with more than 95% of the hydrogen produced by steam-methane reforming (SMR) of natural gas. SMR is attractive because of its high hydrogen yield; but it also converts the carbon to carbon dioxide. Non-oxidative thermal decomposition of methane to carbon and hydrogen is an alternative to SMR and produces CO 2 -free hydrogen. The produced carbon can be sold as a co-product, thus providing economic credit that reduces the delivered net cost of hydrogen. The combination of producing hydrogen with potentially valuable carbon byproducts has market value in that this allows greater flexibility to match the market prices of hydrogen and carbon. That is, the higher value product can subsidize the other in pricing decisions. In this report we highlight the relevant technologies reported in the literature—primarily thermochemical and plasma conversion processes—and recent research progress and commercial activities. Longstanding technical challenges include the high energetic requirements (e.g., high temperatures and/or electricity requirements) necessary for methane activation and, for some catalytic processes, the separation of solid carbon product from the spent catalyst. We assess current and new carbon product markets that could be served given technological advances, and we discuss technical barriers and potential areas of research to address these needs. We provide preliminary economic analysis for these processes and compare to other emerging (e.g., electrolysis) and conventional (e.g., SMR) processes for hydrogen production. The overarching conclusion of this study is that the cost of hydrogen can be potentially reduced to target levels of $2/kg with the co-production and sale of a sufficiently high-value carbon product. Technological advances are required to understand the reaction conditions and design reactor systems that can achieve high yields of the select carbon products and segregate or separate the high-value carbon products, and optimize the production process for both hydrogen and carbon.

30 DIRECT ENERGY CONVERSION↗
DOE OSTI2016

Distributed Halide

Many image processing tasks are naturally expressed as a pipeline of small computational kernels known as stencils. Halide is a popular domain-specific language and compiler designed to implement image processing algorithms. Halide uses simple language constructs to express what to compute and a separate scheduling co-language for expressing when and where to perform the computation. This approach has demonstrated performance comparable to or better than hand-optimized code. Until now, however, Halide has been restricted to parallel shared memory execution, limiting its performance for memory-bandwidth-bound pipelines or large-scale image processing tasks. We present an extension to Halide to support distributed-memory parallel execution of complex stencil pipelines. These extensions compose with the existing scheduling constructs in Halide, allowing expression of complex computation and communication strategies. Existing Halide applications can be distributed with minimal changes, allowing programmers to explore the tradeoff between recomputation and communication with little effort. Approximately 10 new of lines code are needed even for a 200 line, 99 stage application. On nine image processing benchmarks, our extensions give up to a 1.4× speedup on a single node over regular multithreaded execution with the same number of cores, by mitigating the effects of non-uniform memory access. The distributed benchmarks achieve up to 18× speedup on a 16 node testing machine and up to 57× speedup on 64 nodes of the NERSC Cori supercomputer.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

Usefulness of effective field theory for boosted Higgs production

The Higgs + jet channel at the LHC is sensitive to the effects of new physics both in the total rate and in the transverse momentum distribution at high pT . We examine the production process using an effective field theory (EFT) language and discussing the possibility of determining the nature of the underlying high-scale physics from boosted Higgs production. The effects of heavy color triplet scalars and top partner fermions with TeV scale masses are considered as examples and Higgs-gluon couplings of dimension-5 and dimension-7 are included in the EFT. As a byproduct of our study, we examine the region of validity of the EFT. Dimension-7 contributions in realistic new physics models give effects in the high pT tail of the Higgs signal which are so tiny that they are likely to be unobservable.

HEPPH↗
DOE OSTI2015

Neutron interaction and their transport with bulk materials

In the current paper an attempt was made to study and provide fundamental information about neutron interactions that are important to nuclear material measurements. The application of this study is explained about macroscopic interactions with bulk compound materials through a program in DEV C++ language which is done by enabling interaction of neutrons in nature. The output of the entire process depends upon the random number (i.e., incident neutron number), thickness of the material and mean free path as input parameters. Further the current study emphasizes on the usage of materials in shielding.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2016

Verifying quantitative reliability for programs that execute on unreliable hardware

Emerging high-performance architectures are expected to contain unreliable components that may exhibit soft errors, which silently corrupt the results of computations. Full detection and masking of soft errors is challenging, expensive, and, for some applications, unnecessary. For example, approximate computing applications (such as multimedia processing, machine learning, and big data analytics) can often naturally tolerate soft errors. We introduce Rely, a programming language that enables developers to reason about the quantitative reliability of an application—namely, the probability that it produces the correct result when executed on unreliable hardware. Rely allows developers to specify the reliability requirements for each value that a function produces. We perform a static quantitative reliability analysis that verifies quantitative requirements on the reliability of an application, enabling a developer to perform sound and verified reliability engineering. The analysis takes a Rely program with a reliability specification and a hardware specification that characterizes the reliability of the underlying hardware components and verifies that the program satisfies its reliability specification when executed on the underlying unreliable hardware platform. We demonstrate the application of quantitative reliability analysis on six computations implemented in Rely.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2016

Approaches for Communicating Technical Information - 16012

Projects within the nuclear industry are generally complex and associated with high hazards. To achieve success there is often a necessity to apply innovation or adopt longer term strategies and solutions. Because of these long timescales and the fact that some approaches revolve around allowing natural radioactive decay to take place prior to visible action, the industry is sometimes perceived to be technically unable to make progress with its environmental and waste management obligations. Work within the industry additionally takes on a high profile and invariably creates greater levels of anxiety and mistrust in the eyes of stakeholders than comparable projects from non-nuclear related industries. Many aspects of the industry are still seen as secretive, environmentally detrimental and 'risky' and all components of the nuclear life-cycle are therefore open to external scrutiny. Although communication and engagement has increased greatly over the years, especially in developed countries, there is still room for improvement in this field. Such improvement might relate to the frequency and level of engagement, the subject matter or the actual process itself. Communication with stakeholders is required throughout the various phases of the nuclear lifecycle whether the activity relates to mining/milling of uranium, fuel production, operational plant activities, decommissioning, remediation or waste management. The concerns and aspirations of stakeholders during these different activities will vary but need to be adequately addressed. Some organisations now have a basic engagement program and convince themselves that they are carrying out true engagement. But just ticking a box to say that an engagement program is in place does not provide evidence of its appropriateness or success as on many occasions' organisations might still not understand how to adequately engage and communicate technical information. It is not always the information we choose to communicate but that which might be withheld that is often perceived to be most relevant to the stakeholder community. Communicating technical information isn't as straightforward as it sounds, but still has to be undertaken, otherwise trust, understanding and acceptance of chosen options will not be achieved. I utilise what I call the 'ten principles of engagement' which I believe can help when communicating technical Information in relation to nuclear and radiological matters. These are; 1. Develop Trust. 2. Educating people and providing information in a transparent manner. 3. Develop an engagement process that is truly a two way process. 4. Openly discuss risk perception and risk communication. 5. Never try to trivialise risk. 6. Where possible, simplify the language you use. 7. Put background and naturally occurring radioactivity into context. 8. Explain how radioactive materials are often used in everyday life. 9. Try to demonstrate that you too are a member of the public. 10.Walk the talk - Try to undertake what you wish others to undertake. Further research is being undertaken to determine if Mental Models might assist with the communication of nuclear and radiological information. A mental model is an explanation of someone's thought process about how something works in the real world. The mental model approach aims to investigate the judgment and decision-making processes of both expert and lay groups, thus allowing a comparison and visualisation of the different views to be made. It is undoubtedly worthwhile keeping a watching brief on the outcome of such research as we strive to improve our communication with the general public. The aim of this paper is to highlight some simple principles and approaches that can assist with the communication of technical information. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2024

Dynamic Retrieval Augmented Generation of Ontologies using Artificial Intelligence (DRAGON-AI)

Ontologies are fundamental components of informatics infrastructure in domains such as biomedical, environmental, and food sciences, representing consensus knowledge in an accurate and computable form. However, their construction and maintenance demand substantial resources and necessitate substantial collaboration between domain experts, curators, and ontology experts. We present Dynamic Retrieval Augmented Generation of Ontologies using AI (DRAGON-AI), an ontology generation method employing Large Language Models (LLMs) and Retrieval Augmented Generation (RAG). DRAGON-AI can generate textual and logical ontology components, drawing from existing knowledge in multiple ontologies and unstructured text sources.We assessed performance of DRAGON-AI on de novo term construction across ten diverse ontologies, making use of extensive manual evaluation of results. Our method has high precision for relationship generation, but has slightly lower precision than from logic-based reasoning. Our method is also able to generate definitions deemed acceptable by expert evaluators, but these scored worse than human-authored definitions. Notably, evaluators with the highest level of confidence in a domain were better able to discern flaws in AI-generated definitions. We also demonstrated the ability of DRAGON-AI to incorporate natural language instructions in the form of GitHub issues.These findings suggest DRAGON-AI's potential to substantially aid the manual ontology construction process. However, our results also underscore the importance of having expert curators and ontology editors drive the ontology generation process.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗