Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Domain-specific learning”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
NASA NTRS1993

Newly available technologies present expanding opportunities for scientific and technical information exchange

The potential for expanded communication among researchers, scholars, and students is supported by growth in the capabilities for electronic communication as well as expanding access to various forms of electronic interchange and computing capabilities. Increased possibilities for information exchange, collegial dialogue, collaboration, and access to remote resources exist as high-speed networks, increasingly powerful workstations, and large, multi-user computational facilities are more frequently linked and more commonly available. Numerous writers speak of the telecommunications revolution and its impact on the development and dissemination of knowledge and learning. One author offers the phrase 'Scholarly skywriting' to represent a new form of scientific communication that he envisions using electronic networks. In the United States (U.S.), researchers associated with the National Science Foundation (NSF) are exploring 'nationwide collaboratories' and 'digital collaboration.' Research supported by the U.S. National Aeronautics and Space Administration (NASA) points to a future where workstations with built-in audio, video monitors, and screen sharing protocols are used to support collaborations with colleagues located throughout the world. Instruments and sensors located worldwide will produce data streams that will be brought together, analyzed, and distributed as new findings. Researchers will have access to machines that can supply domain-specific information in addition to locator and directory assistance. New forms of electronic journals will emerge and provide opportunities for researchers and scientists to exchange information electronically and interactively in a range of structures and formats. Ultimately, the wide-scale use of these technologies in the dissemination of research results and the stimulation of collegial dialogue will change the way we represent and express our knowledge of the world. A new paradigm will evolve--perhaps a truly worldwide 'invisible college.'

Tolzman, Jean M.↗
DOE OSTI2025

Seeing is Believing: Autonomous Microscopy and the Data Revolution in Materials Science [Slides]

Machine intelligence has the potential to revolutionize materials science, enabling autonomous synthesis, self-driving characterization, and accelerated modeling. However, despite the promise, successful implementation of these methods in day-to-day research remains a challenge. This talk will delve into the reasons behind this, exploring how truly intelligent experiments are hindered by opaque experiment control, a lack of domain-specific models, and human-centric design. Through a focus on the characterization of next-generation microelectronics and energy storage materials, I will share insights from both successful and failed attempts to implement machine intelligence. We will then explore the next steps necessary to unlock the full potential of machine intelligence in materials science, creating a future where intelligent systems work seamlessly alongside researchers to drive innovation and discovery.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Roadmap for unconventional computing with nanotechnology

Abstract In the ‘Beyond Moore’s Law’ era, with increasing edge intelligence, domain-specific computing embracing unconventional approaches will become increasingly prevalent. At the same time, adopting a variety of nanotechnologies will offer benefits in energy cost, computational speed, reduced footprint, cyber resilience, and processing power. The time is ripe for a roadmap for unconventional computing with nanotechnologies to guide future research, and this collection aims to fill that need. The authors provide a comprehensive roadmap for neuromorphic computing using electron spins, memristive devices, two-dimensional nanomaterials, nanomagnets, and various dynamical systems. They also address other paradigms such as Ising machines, Bayesian inference engines, probabilistic computing with p-bits, processing in memory, quantum memories and algorithms, computing with skyrmions and spin waves, and brain-inspired computing for incremental learning and problem-solving in severely resource-constrained environments. These approaches have advantages over traditional Boolean computing based on von Neumann architecture. As the computational requirements for artificial intelligence grow 50 times faster than Moore’s Law for electronics, more unconventional approaches to computing and signal processing will appear on the horizon, and this roadmap will help identify future needs and challenges. In a very fertile field, experts in the field aim to present some of the dominant and most promising technologies for unconventional computing that will be around for some time to come. Within a holistic approach, the goal is to provide pathways for solidifying the field and guiding future impactful discoveries.

Finocchio, Giovanni (ORCID:0000000210433876)↗
DOE OSTI2023

GAHLS: an optimized graph analytics based high level synthesis framework

The urgent need for low latency, high-compute and low power on-board intelligence in autonomous systems, cyber-physical systems, robotics, edge computing, evolvable computing, and complex data science calls for determining the optimal amount and type of specialized hardware together with reconfigurability capabilities. With these goals in mind, we propose a novel comprehensive graph analytics based high level synthesis (GAHLS) framework that efficiently analyzes complex high level programs through a combined compiler-based approach and graph theoretic optimization and synthesizes them into message passing domain-specific accelerators. This GAHLS framework first constructs a compiler-assisted dependency graph (CaDG) from low level virtual machine (LLVM) intermediate representation (IR) of high level programs and converts it into a hardware friendly description representation. Next, the GAHLS framework performs a memory design space exploration while account for the identified computational properties from the CaDG and optimizing the system performance for higher bandwidth. The GAHLS framework also performs a robust optimization to identify the CaDG subgraphs with similar computational structures and aggregate them into intelligent processing clusters in order to optimize the usage of underlying hardware resources. Finally, the GAHLS framework synthesizes this compressed specialized CaDG into processing elements while optimizing the system performance and area metrics. Evaluations of the GAHLS framework on several real-life applications (e.g., deep learning, brain machine interfaces) demonstrate that it provides 14.27× performance improvements compared to state-of-the-art approaches such as LegUp 6.2.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

SRBench++: Principled Benchmarking of Symbolic Regression With Domain-Expert Interpretation

Symbolic regression searches for analytic expressions that accurately describe studied phenomena. The main promise of this approach is that it may return an interpretable model that can be insightful to users, while maintaining high accuracy. The current standard for benchmarking these algorithms is SRBench, which evaluates methods on hundreds of datasets that are a mix of real-world and simulated processes spanning multiple domains. At present, the ability of SRBench to evaluate interpretability is limited to measuring the size of expressions on real-world data, and the exactness of model forms on synthetic data. In practice, model size is only one of many factors used by subject experts to determine how interpretable a model truly is. Furthermore, SRBench does not characterize algorithm performance on specific, challenging sub-tasks of regression such as feature selection and evasion of local minima. In this work, we propose and evaluate an approach to benchmarking SR algorithms that addresses these limitations of SRBench by 1) incorporating expert evaluations of interpretability on a domain-specific task, and 2) evaluating algorithms over distinct properties of data science tasks. We evaluate 12 modern symbolic regression algorithms on these benchmarks and present an in-depth analysis of the results, discuss current challenges of symbolic regression algorithms and highlight possible improvements for the benchmark itself.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Explainable tokamak-agnostic forecasting of fusion plasma instability via megahertz turbulent fluctuations

Scientific applications of artificial intelligence (AI) often remain limited by device-specific training and unexplained “black-box” approaches, creating fundamental barriers to cross-system generalization. This challenge is critical for nuclear fusion, where future reactors will have limited operational data for AI training. Here, we demonstrate that our neural network, trained solely on megahertz-scale turbulence measurements from one machine (DIII-D), forecasts Type-I edge localized mode (ELM) onsets in a different tokamak (KSTAR) through zero-shot weight transfer following physics-consistent preprocessing without device-specific retraining. Through an explainable AI framework combining gradient-weighted class activation mapping with physics validation, we reveal that our network can internalize physics relationships governing the ELM instabilities rather than memorizing device-specific patterns. The network perceives spatiotemporal features that correlate consistently with independently calculated instability growth rates, magnetohydrodynamic stability limits, and pedestal structure dynamics. Statistical analyses of dimensionally-reduced saliency features reveal the identical triangular features between the saliency representations, instability growth rates, and prediction probability across tokamaks, providing evidence that our forecasting system can show tokamak-agnostic generalization. This work contributes to a foundation for explainable scientific AI systems, where cross-system developments are essential for transcending traditional domain-specific constraints.

AI↗
DOE OSTI2025

Causal discovery from data assisted by large language models

Knowledge-driven discovery of novel materials necessitates the development of causal models for property emergence. While in the classical physical paradigm, the causal relationships are deduced based on physical principles or via experiment, the rapid accumulation of observational data necessitates learning causal relationships between dissimilar aspects of material structure and functionalities based on observations. For this, it is essential to integrate experimental data with prior domain knowledge. Here, we demonstrate this approach by combining high-resolution scanning transmission electron microscopy data with insights derived from large language models (LLMs). By applying ChatGPT to domain-specific literature, such as arXiv papers on ferroelectrics, and combining the obtained information with data-driven causal discovery, we construct adjacency matrices for directed acyclic graphs that map the causal relationships between structural, chemical, and polarization degrees of freedom in Sm-doped BiFeO 3 . This approach enables us to hypothesize how synthesis conditions influence material properties and guides experimental validation. Furthermore, the ultimate objective of this work is to develop a unified framework that integrates LLM-driven literature analysis with data-driven discovery, facilitating the precise engineering of ferroelectric materials by establishing clear connections between synthesis conditions and their resulting material properties.

Causal inference↗
NASA NTRSDate not supplied

2022 Spring Internship Exit Presentation

As efforts of the National Aeronautics and Space Administration (NASA) and the Federal Aviation Administration (FAA) continue to digitize the air traffic management (ATM) domain, there is countless times of need for downstream natural language processing (NLP) tasks such as named entity recognition, text summarization, classification, and more. Although there are a plethora of open-sourced pre-trained transformer models in the NLP field such as BERT, RoBERTa, XLNet, and GPT-3, these models are trained on general corpora and perform poorly on domain-specific terminology and phraseology seen in ATM documents such as Notice to Airmen (NOTAMs) and Letters of Agreement (LoA). Our proposed research objective will be to first gather a large corpus of air traffic management related documents, orders, notices, books, technical papers, conference papers, articles, and other miscellaneous sources of text data from the FAA, NASA, and accredited conference and publication societies. After gathering this data, many steps will have to be taken to collate and preprocess the data into a format understandable by our test transformer models. Thirdly, we will set up training pipelines to train the RoBERTa model on its unsupervised training task masked language modelling (MLM) using resources provided by the NASA Advanced Supercomputing (NAS) facilities. Finally, these fine-tuned transformer models will be evaluated on their performance on down-stream NLP tasks as mentioned above, to show whether they will be effective when working with ATM related data or not. Once complete, this model could be made open-sourced on the HuggingFace website, where the rest of the ATM community can access and utilize this tool.

NLP↗
DOE OSTI2026

PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Background Protein language models (PLMs) have revolutionized protein fitness prediction, yet their application to rapidly evolving viral pathogens is often confounded by extreme sequence homology. This homology leads to “data leakage” in standard random validation splits, yielding inflated performance metrics that fail to translate into real-world biosurveillance utility. Results We present Protein Representation Inference for Mutation Evaluation (PRIME), a framework that integrates domain-specific fine-tuning with a rigorous position-stratified validation protocol to evaluate viral threats. Using a dataset of 347,432 SARS-CoV-2 receptor binding domain (RBD) sequences, we demonstrate that while random training data split yields deceptive R 2 values (> 0.90), they fail to generalize to novel mutational sites. By benchmarking models up to 650 M parameters, we show that domain-specific fine-tuning of the ESM-C 600 M model with correctly stratified data provides an initial demonstration of predictive signal for binding affinity and expression at unseen mutational sites of binding affinity and expression on unseen sites (R 2 ~0.23), a significant advancement over base foundation models which exhibit no predictive power (R 2 <0). PRIME’s embedding-based clustering identified 3.03% of bat coronavirus sequences as candidates for further experimental prioritization based on their functional similarity to human-infective strains in embedding space, offering a perspective complementary to traditional phylogenetic methods. Conclusion PRIME establishes a new benchmark for the application of PLMs in pathogen surveillance. Our findings demonstrate that state-of-the-art models and fine-tuning, when paired with stratified validation, provide biologically meaningful insights into pathogen evolution and zoonotic risk.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Text Mining for Process–Structure–Properties Relationships in Metals

With the advent of large language models (LLMs), the vast unstructured text within millions of academic papers is increasingly accessible for materials discovery—although significant challenges remain. While LLMs offer promising few- and zero-shot learning capabilities, particularly valuable in the materials domain where expert annotations are scarce, general-purpose LLMs often fail to address key materials-specific queries without further adaptation. To bridge this gap, fine-tuning LLMs on human-labeled data is essential for effective structured knowledge extraction (Liu in The Importance of Human-Labeled Data in the Era of LLMs, 2023). Here, in this study, we introduce a novel annotation schema designed to extract generic process–structure–properties relationships from scientific literature. We demonstrate the utility of this approach using a dataset of 128 abstracts, with annotations drawn from two distinct domains: high-temperature materials (Domain I) and uncertainty quantification in simulating materials microstructure (Domain II). Initially, we developed a conditional random field (CRF) model based on MatBERT—a domain-specific BERT variant—and evaluated its performance on Domain I. Subsequently, we compared this model with a fine-tuned LLM (GPT-4o from OpenAI) under identical conditions. Our results indicate that fine-tuning LLMs can significantly improve entity extraction performance over the BERT-CRF baseline on Domain I. However, when additional examples from Domain II were incorporated, the performance of the BERT-CRF model became comparable to that of the GPT-4o model. These findings underscore the potential of our schema for structured knowledge extraction and highlight the complementary strengths of both modeling approaches.

Materials science↗
DOE OSTI2025

Impact of Domain Knowledge on the Property Prediction of Specialized Machine Learning Models

Developing transferable machine learning models is trending in data-driven materials research. However, how to apply such models to a specific research domain remains unclear. Here, in this work, we choose high-entropy materials as a platform with a specialized data set containing 145,323 DFT-relaxed materials. This data set is used to explore the role of domain-specific knowledge in training effective models. Our tests with three representative graph neural network architectures indicate the model complexity has much smaller influence on performance than the data itself. Specifically, the consideration of low-energy atomic ordering, structures with diverse elemental coverage, and high-order interactions significantly influences the model performance. We also find that domain knowledge-driven sampling can greatly enhance unsupervised learning techniques. This research highlights that developing specialized data sets is more beneficial than further complicating deep learning architectures. Additionally, physics-inspired sampling algorithms are crucially needed for better machine learning models for a specific materials research domain.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Engineering modular enzyme assembly: synthetic interface strategies for natural products biosynthesis applications

Covering: 2020 to 2025Natural products remain indispensable sources of therapeutic and bioactive compounds, yet traditional discovery strategies are constrained by compound rediscovery. Modular biosynthetic enzymes, such as type I polyketide synthases (PKSs) and type A non-ribosomal peptide synthetases (NRPSs), offer promising platforms for combinatorial biosynthesis owing to their programmable architectures. However, practical implementation is frequently limited by inter-modular incompatibility and domain-specific interactions. This review highlights recent advances in modular enzyme assembly enabled by synthetic interfaces-including cognate docking domains, synthetic coiled-coils, SpyTag/SpyCatcher, and split inteins-which function as orthogonal, standardized connectors to facilitate post-translational complex formation. These interfaces support rational investigations into substrate specificity, module compatibility, and pathway derivatization as well as general enzyme clustering applications beyond PKS and NRPS systems. Synthetic interfaces can be integrated with computational tools to support a more systematic and scalable framework for modular enzyme engineering by providing predictive insights into domain compatibility and interface design. These approaches within iterative design-build-test-learn workflows can accelerate the programmable assembly of biosynthetic systems and expand the accessible chemical space for natural products.

Kim, Gahyeon↗
DOE OSTI2024

Automated annotation of scientific texts for ML-based keyphrase extraction and validation

Advanced omics technologies and facilities generate a wealth of valuable data daily; however, the data often lack the essential metadata required for researchers to find, curate, and search them effectively. The lack of metadata poses a significant challenge in the utilization of these data sets. Machine learning (ML)–based metadata extraction techniques have emerged as a potentially viable approach to automatically annotating scientific data sets with the metadata necessary for enabling effective search. Text labeling, usually performed manually, plays a crucial role in validating machine-extracted metadata. However, manual labeling is time-consuming and not always feasible; thus, there is a need to develop automated text labeling techniques in order to accelerate the process of scientific innovation. This need is particularly urgent in fields such as environmental genomics and microbiome science, which have historically received less attention in terms of metadata curation and creation of gold-standard text mining data sets. In this paper, we present two novel automated text labeling approaches for the validation of ML-generated metadata for unlabeled texts, with specific applications in environmental genomics. Our techniques show the potential of two new ways to leverage existing information that is only available for select documents within a corpus to validate ML models, which can then be used to describe the remaining documents in the corpus. The first technique exploits relationships between different types of data sources related to the same research study, such as publications and proposals. The second technique takes advantage of domain-specific controlled vocabularies or ontologies. In this paper, we detail applying these approaches in the context of environmental genomics research for ML-generated metadata validation. Our results show that the proposed label assignment approaches can generate both generic and highly specific text labels for the unlabeled texts, with up to 44% of the labels matching with those suggested by a ML keyword extraction algorithm.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2024

INSURE: An Information Theory iNspired diSentanglement and pURification modEl for Domain Generalization

Domain Generalization (DG) aims to learn a generalizable model on the unseen target domain by only training on the multiple observed source domains. Although a variety of DG methods have focused on extracting domain-invariant features, the domain-specific class-relevant features have attracted attention and been argued to benefit generalization to the unseen target domain. To take into account the class-relevant domain-specific information, in this paper we propose an Information theory iNspired diSentanglement and pURification modEl (INSURE) to explicitly disentangle the latent features to obtain sufficient and compact (necessary) class-relevant feature for generalization to the unseen domain. Specifically, we first propose an information theory inspired loss function to ensure the disentangled class-relevant features contain sufficient class label information and the other disentangled auxiliary feature has sufficient domain information. Additionally, we further propose a paired purification loss function to let the auxiliary feature discard all the class-relevant information and thus the class-relevant feature will contain sufficient and compact (necessary) class-relevant information. Moreover, instead of using multiple encoders, we propose to use a learnable binary mask as our disentangler to make the disentanglement more efficient and make the disentangled features complementary to each other. We conduct extensive experiments on five widely used DG benchmark datasets including PACS, VLCS, OfficeHome, TerraIncognita, and DomainNet. The proposed INSURE achieves state-of-the-art performance. We also empirically show that domain-specific class-relevant features are beneficial for domain generalization. The code is available at https://github.com/yuxi120407/INSURE .

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1991

Utilizing expert systems for satellite monitoring and control

Spacecraft analysts in the spacecraft control center for the Cosmic Background Explorer (COBE) satellite are currently utilizing a fault-isolation expert system developed to assist in the isolation and correction of faults in the communications link. This system, the communication link expert assistance resource (CLEAR), monitors real time spacecraft and ground systems performance parameters in search of configuration discrepancies and communications link problems. If such a discrepancy or problem is isolated, CLEAR alerts the analyst and provides advice on how to resolve the problem swiftly and effectively. The CLEAR system is the first real time expert system to be used in the operational environment of a satellite control center at the NASA Goddard Space Flight Center. Clear has not only demonstrated the utility and potential of an expert system in the demanding environment of a satellite control center, but also has revealed many of the pitfalls and deficiencies of development of expert systems. One of the lessons learned from this and other initial expert system projects is that prototypes can often be developed quite rapidly, but operational expert systems require considerable effort. Development is generally a slow, tedious process that typically requires the special skills of trained programmers. Due to the success of CLEAR and several other systems in the control center domain, a large number of expert systems will certainly be developed to support control center operations during the early 1990's. To facilitate the development of these systems, a project was initiated to develop an integrated, domain-specific tool, the generic spacecraft analyst assistent (GenSAA), that alows the spacecraft analysts to rapidly create simple expert systems themselves. By providing a highly graphical point-and-select method of system development, GenSAA allows the analyst to utilize and/or modify previously developed rule bases and system components; thus, facilitating software reuse and reducing development time and effort.

Hughes, Peter M.↗
NASA NTRS1993

Learning Search Control Knowledge for Deep Space Network Scheduling

While the general class of most scheduling problems is NP-hard in worst-case complexity, in practice, for specific distributions of problems and constraints, domain-specific solutions have been shown to perform in much better than exponential time.

Deep Space Network Search Control↗
NASA NTRSDate not supplied

SafeAeroBERT: Towards a Safety-Informed Aerospace-Specific Language Model

As aviation systems continue to operate with high traffic, large amounts of documents containing safety-relevant data continue to be generated via reporting systems such as the Aviation Safety Reporting System (ASRS). Advanced natural language processing techniques, specifically pre-trained language models, have shown great success in domain-specific applications; however, the text in aviation safety reports is inundated with jargon and thus not fully utilized by general pre-trained models. In this research, we work towards developing a safety-informed aerospace-specific language model by pre-training a Bidirectional Encoder Representations from Transformer (BERT) model on reports from the Aviation Safety Reporting System and the National Transportation Safety Board. The resulting model, called SafeAeroBERT, is fine-tuned for the specific task of document classification, and can be further tuned for named-entity recognition, relation detection, information retrieval, and summarization. Results from the classification task are compared between SafeAeroBERT, the base BERT, and SciBERT models and show SafeAeroBERT outperforms the general BERT and SciBERT on classifying reports about weather and procedure. SafeAeroBERT can be used on custom tasks, not limited to document classification, and is intended to aid an intelligent knowledge manager for safety report repositories.

Aviation↗
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↗