Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “information extraction”

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 19 records

Relationship Extraction: Automatic Information Extraction and Organization for Supporting Analysts in Threat Assessment

In order for analysts to be able to do their work, they sift through hundreds, thousands, or even millions of documents to make connections between entities of interest. This process is time consuming, tedious, and prone to potential error from missed connections or connections made that should not have been. There exist many tools in natural language processing, or NLP, to extract information from documents. However, when it comes to relationship extraction, there has been varied success. This project began with a goal to solve the relationship extraction problem which developed into a deeper understanding of the problem and the associated challenges for solving this problem on a general scale. In this report, we explain our research and approach to relationship extraction, identify other auxiliary problems in NLP that provide additional challenges to solving relationship extraction generally, explain our analysis of the current state of relationship extraction, and postulate future work to address these problems.

97 MATHEMATICS AND COMPUTING↗

Challenges and Advances in Information Extraction from Scientific Literature: a Review

Scientific articles have long been the primary means of disseminating scientific discoveries. Over the centuries, valuable data and potentially groundbreaking insights have been collected and buried deep in the mountain of publications. In materials engineering, such data are spread across technical handbooks specification sheets, journal articles, and laboratory notebooks in myriad formats. Extracting information from papers on a large scale has been a tedious and time-consuming job to which few researchers have wanted to devote their limited time and effort, yet is an activity that is essential for modern data-driven design practices. However, in recent years, significant progress has been made by the computer science community on techniques for automated information extraction from free text. Yet, transformative application of these techniques to scientific literature remains elusive-due not to a lack of interest or effort but to technical and logistical challenges. Using the challenges in the materials science literature as a driving motivation, we review the gaps between state-of-the-art information extraction methods and the practical application of such methods to scientific texts, and offer a comprehensive overview of work that can be undertaken to close these gaps.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Automatic information extraction from neutron radiography imaging to estimate axial fuel expansion in $\mathrm{EBR-II}$

Approximately 130,000 metal fuel pins were irradiated in the Experimental Breeder Reactor II (EBR-II) during its 30 years of operation to develop and characterize existing and prospective fuels. For many of the metal fuel irradiation experiments, neutron radiography imaging was performed to characterize fuel behavior, like fuel swelling. However, due to the lack of technology or resources, many of the images have not been processed or were processed manually through visual examination. This paper represents first-attempt to develop an image processing algorithm capable of automatically extracting information regarding the degree of fuel swelling from neutron radiography imaging. The algorithm was applied to 120 images of three different metallic fuel pin compositions—U-10Zr, U-8Pu-10Zr, and U-19Pu-10Zr. The algorithm performs operations of image intensity adjustment, image binarization, region finding, and labeling to extract information about fuel swelling. The average growth for U-10Zr was found to be 8.49% with 95% Confidence Interval (CI) [8.33 –8.66%], for U-8Pu-10Zr — 7.50% with 95% CI [7.23 – 7.78%], and for U-19Pu-10Zr — 3.15%, with 95% CI [2.40 – 3.91%]. The results obtained by applying this automatic image processing algorithm are consistent with previously reported studies of the same types of fuels. The automatic image processing algorithm will be expanded to include thousands of available neutron radiography images and different types of fuels to investigate empirical dependencies of fuel swelling, which can be subsequently applied to advanced fuel modeling. Results from this study can later be compared to BISON simulations to further benchmark modeling efforts and develop assessment cases.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

How Beneficial Is Pretraining on a Narrow Domain-Specific Corpus for Information Extraction about Photocatalytic Water Splitting?

Language models trained on domain-specific corpora have been employed to increase the performance in specialized tasks. However, little previous work has been reported on how specific a “domain-specific” corpus should be. Here, we test a number of language models trained on varyingly specific corpora by employing them in the task of extracting information from photocatalytic water splitting. We find that more specific corpora can benefit performance on downstream tasks. Furthermore, PhotocatalysisBERT, a pretrained model from scratch on scientific papers on photocatalytic water splitting, demonstrates improved performance over previous work in associating the correct photocatalyst with the correct photocatalytic activity during information extraction, achieving a precision of 60.8(+11.5)% and a recall of 37.2(+4.5)%.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

The ISES: A non-intrusive medium for in-space experiments in on-board information extraction

The Information Science Experiment System (ISES) represents a new approach in applying advanced systems technology and techniques to on-board information extraction in the space environment. Basically, what is proposed is a 'black box' attached to the spacecraft data bus or local area network. To the spacecraft the 'black box' appears to be just another payload requiring power, heat rejection, interfaces, adding weight, and requiring time on the data management and communication system. In reality, the 'black box' is a programmable computational resource which eavesdrops on the data network, taking and producing selectable, real-time science data back on the network. This paper will present a brief overview of the ISES Concept and will discuss issues related to applying the ISES to the polar platform and Space Station Freedom. Critical to the operation of ISES is the viability of a payload-like interface to the spacecraft data bus or local area network. Study results that address this question will be reviewed vis-a-vis the solar platform and the core space station. Also, initial results of processing science and other requirements for onboard, real-time information extraction will be presented with particular emphasis on the polar platform. Opportunities for a broader range of applications on the core space station will also be discussed.

Murray, Nicholas D.↗

Retrofitting Word Embeddings with the UMLS Metathesaurus for Clinical Information Extraction

Deep learning has surged in popularity and proven to be effective for various artificial intelligence applications including information extraction from cancer pathology reports. Since word representation is a core unit that enables deep learning algorithms to understand words and be able to perform NLP, this representation must include as much information as possible to help these algorithms achieve high classification performance. Therefore, in this work in addition to the distributional information of words in large sized corpora, we use UMLS vocabulary resources to enrich the vector space representation of words with the semantic relations between words. These resources provide many terminologies pertaining to cancer. The refined word embeddings are used with a convolutional neural (CNN) model to extract four data elements from cancer pathology reports; ICD-O-3 tumor topography codes, tumor laterality, behavior, and histological grade. We observed that using UMLS vocabulary resources to enrich word embeddings of CNN models consistently outperformed CNN models without pre-training word embeddings and even with pre-trained word embeddings on a domain specific corpus across all four tasks. The results show marginal improvement on the laterality task, but a significant improvement on the other tasks, especially for the macro-f score. Specifically, the improvements are 3%, 13%, and 15% for tumor site, histological grade, and behavior tasks, respectively. This approach is encouraging to enrich word embeddings with more clinical data resources to be used for information abstraction tasks from clinical pathology reports.

Alawad, Mohammed↗

Information extraction system

An information extraction system and methods of operating the system are provided. In particular, an information extraction system for performing meta-extraction of named entities of people, organizations, and locations as well as relationships and events from text documents are described herein.

97 MATHEMATICS AND COMPUTING↗

Deep Transfer Learning Across Cancer Registries for Information Extraction from Pathology Reports

Automated text information extraction from cancer pathology reports is an active area of research to support national cancer surveillance. A well-known challenge is how to develop information extraction tools with robust performance across cancer registries. In this study we investigated whether transfer learning (TL) with a convolutional neural network (CNN) can facilitate cross-registry knowledge sharing. Specifically, we performed a series of experiments to determine whether a CNN trained with single-registry data is capable of transferring knowledge to another registry or whether developing a cross-registry knowledge database produces a more effective and generalizable model. Using data from two cancer registries and primary tumor site and topography as the information extraction task of interest, our study showed that TL results in 6.90% and 17.22% improvement of classification m acro F -score o ver the baseline single-registry models. Detailed analysis illustrated that the observed improvement is evident in the low prevalence classes.

Alawad, Mohammed↗

Scaling open-weight large language models for hydropower regulatory information extraction: A systematic analysis

Information extraction from regulatory and technical documents using large language models (LLMs) involves practical trade-offs between extraction quality and computational cost. We evaluate eight open-weight LLMs spanning 0.6B–70B parameters on hydropower licensing documents and report deployment-oriented evidence under a unified extraction schema and evaluation protocol. Across the model set, we observe clear scale-dependent trends in both baseline extraction quality and the effectiveness of reflective reasoning (self-checking) under our fixed-prompt, no-augmentation setting. Mid-scale models often provide a favorable balance of accuracy and efficiency, whereas the smallest models show limited or inconsistent gains from the reasoning variants tested. Larger models achieve the highest overall F1 scores but incur substantially greater compute and infrastructure requirements. We further find that reliability failure modes can distort conventional metrics in this domain: in particular, high recall can coincide with systematic extraction errors when models fabricate values for fields that are absent from the source text, underscoring the importance of conservative null handling and evidence-grounded evaluation. Overall, our study provides a reproducible resource–performance comparison for open-weight LLM-based extraction in hydropower regulatory documentation and offers practical guidance for model selection under different deployment constraints.

Evaluation protocol↗

Coarse-to-Fine Multi-Task Training of Convolutional Neural Networks for Automated Information Extraction from Cancer Pathology Reports

Information extraction and coding of free-text pathology reports is an important activity for cancer registries to support national cancer surveillance. Cancer registrars must process high volumes of pathology reports on an annual basis. In this study, we investigated an automated approach using a coarse-to-fine training of convolutional neural networks (CNNs) for extracting the primary site, histological grade and laterality from unstructured cancer pathology text reports. Our proposed training scheme consists of two stages. In the first stage, the multi-task learning (MTL) with hard parameter sharing approach is used to train a multi-task MT-CNN model for all the tasks. Then, the TM-CNN parameters are used to initialize a CNN model for each task to be fine trained individually using its corresponding dataset. The performance of our proposed model was compared against a state-of-the-art CNN and the commonly used SVM classifier. We observed that the proposed model consistently outperformed the base line models, especially for the less prevalent classes. Specifically, the proposed training approach achieved a micro-F score of 0.7749 over 12 ICD- O-3 topography codes which is a significant improvement as compared with state-of-the-art CNN (0.7101) and the SVM (0.6019) classifiers. Also, the results demonstrate the potential of the proposed method for handling class imbalance within each task. It significantly improves macro-F score by 24% and 12% of the primary site and histology grade tasks, respectively.

Alawad, Mohammed↗

Advances in information extraction techniques

Sundry recent developments are presented which show some potential for affecting the automatic extraction of information from remotely sensed data. Pattern representations more abstract than Euclidean vector spaces offer some hope of unifying structural and decision theoretical approaches. The estimation of expected classification error rates is becoming more sophisticated and rigorous, but useful finite-sample results for nonparametric distributions appear unobtainable. Focus on computational complexity allows comparison of algorithms, while software engineering techniques reduce the effort necessary to develop and maintain complex image processing systems. Advances in computer systems architecture, commercial database technology, and man-machine communications should be closely monitored by the remote sensing community. A NASA-sponsored recommendation for research directions in mathematical pattern recognition are offered.

Nagy, G.↗

Advanced processing and information extraction techniques applied to ERTS-1 MSS data

Conventional automatic data processing and information extraction techniques fall short of providing the information required by the user in some applications. For those cases, advanced techniques are needed to permit the extraction of the necessary information. Advanced techniques are described and examples of their application to ERTS-1 MSS data are provided. The techniques are designed to help overcome problems in location, mensuration, and classification accuracies which result from geometric distortions of the ERTS MSS data, the relatively coarse resolution of the sensor, and variations in atmospheric state over the region to be surveyed. It is shown that each of these factors can seriously degrade one's ability to extract necessary information. Further, it is shown that advanced techniques can alleviate the effects of these factors.

Malila, W. A.↗

LLM Information Extraction Toolkit

A modular Python framework for information extraction using large language models with support for multiple backends and optional verification workflows.

Yoon, Hong-Jun [Oak Ridge National Laboratory (ORN↗

Named Entity Recognition and Normalization Applied to Large-Scale Information Extraction from the Materials Science Literature

The number of published materials science articles has increased manyfold over the past few decades. Now, a major bottleneck in the materials discovery pipeline arises in connecting new results with the previously established literature. A potential solution to this problem is to map the unstructured raw text of published articles onto structured database entries that allow for programmatic querying. To this end, we apply text mining with named entity recognition (NER) for large-scale information extraction from the published materials science literature. The NER model is trained to extract summary-level information from materials science documents, including inorganic material mentions, sample descriptors, phase labels, material properties and applications, as well as any synthesis and characterization methods used. Our classifier achieves an accuracy (f 1 ) of 87%, and is applied to information extraction from 3.27 million materials science abstracts. We extract more than 80 million materials-science-related named entities, and the content of each abstract is represented as a database entry in a structured format. We demonstrate that simple database queries can be used to answer complex "meta-questions" of the published literature that would have previously required laborious, manual literature searches to answer. Finally, all of our data and functionality has been made freely available on our Github ( https://github.com/materialsintelligence/matscholar ) and website ( http://matscholar.com ), and we expect these results to accelerate the pace of future materials science discovery.

36 MATERIALS SCIENCE↗

Atmospheric effects in ERTS-1 data, and advanced information extraction techniques

Atmospheric effects in satellite multispectral scanner data can influence results obtained with either manual image interpretation or computer information extraction techniques. The atmosphere attenuates radiation arriving from the surface and adds an extraneous path radiance component. Initial results of an investigation of atmospheric effects in ERTS data are presented. Empirical analyses of ERTS MSS data and simultaneous airborne MSS underflight data for one frame, along with theoretical calculations of atmospheric effects, are discussed. The effect of limited spatial resolution on the accuracy of information extracted from ERTS data also is important. Problems occur when individual resolution elements contain two or more materials. Results from an initial application of ERIM techniques for estimating proportions of materials within individual elements are presented and discussed. Very accurate determination of surface areas of small lakes is achieved.

Malila, W. A.↗

Automatic information extraction from childhood cancer pathology reports

The International Classification of Childhood Cancer (ICCC) facilitates the effective classification of a heterogeneous group of cancers in the important pediatric population. However, there has been no development of machine learning models for the ICCC classification. We developed deep learning-based information extraction models from cancer pathology reports based on the ICD-O-3 coding standard. In this article, we describe extending the models to perform ICCC classification. We developed 2 models, ICD-O-3 classification and ICCC recoding (Model 1) and direct ICCC classification (Model 2), and 4 scenarios subject to the training sample size. We evaluated these models with a corpus consisting of 29206 reports with age at diagnosis between 0 and 19 from 6 state cancer registries. Our findings suggest that the direct ICCC classification (Model 2) is substantially better than reusing the ICD-O-3 classification model (Model 1). Applying the uncertainty quantification mechanism to assess the confidence of the algorithm in assigning a code demonstrated that the model achieved a micro-F1 score of 0.987 while abstaining (not sufficiently confident to assign a code) on only 14.8% of ambiguous pathology reports. Our experimental results suggest that the machine learning-based automatic information extraction from childhood cancer pathology reports in the ICCC is a reliable means of supplementing human annotators at state cancer registries by reading and abstracting the majority of the childhood cancer pathology reports accurately and reliably.

60 APPLIED LIFE SCIENCES↗

Semi-Supervised Information Extraction for Cancer Pathology Reports

Pathology reports are a main source of data for cancer surveillance programs. Manual coding of pathology reports is labor-intensive but necessary for obtaining labeled data to train automated information extraction systems. In this study, we investigated semi-supervised deep learning, improving the performance of a multitask information extraction system for automated annotation of pathology reports. We used a set of over 374,000 pathology reports from the Louisiana Tumor Registry and a novel convolutional attention-based auto-encoder. We performed a set of experiments comparing supervised training augmented with unlabeled data at 1%, 5%, 10%, and 50% of the original data size. We also compared the impact of extending text processing to include unlabeled tokens. We find that semi-supervised training consistently improved individual performance with increased micro-averaged F-scores between 0.012 and 0.064 and increased macro-averaged F-scores of up to 0.158. This demonstrates that semantic information learned via unsupervised learning can be used to improve supervised clinical task performance.

Qiu, John X.↗

Mars Target Encyclopedia: Information Extraction for Planetary Science

We created a new reference database called the Mars Target Encyclopedia (MTE) that contains compositional information about science targets (usually rocks or soils) on Mars. Users can search for all targets that contain an element (e.g., “calcium”) or mineral (e.g., “hematite”) and see a map view of their spatial locations (see Fig. 1). Clicking on a search result or searching for a specific target of interest (e.g., “Dillinger”) brings up a page that compiles previous findings about its composition (see Fig. 2). The information that populates the MTE was mined from the planetary science literature using information extraction technology. All information in the MTE is linked to the source publication from which it was extracted, so users can easily browse the full context in the original document (Fig. 2).

Singh, K.↗