Search NASA⌕ Search

SEARCH · Search NASA

Results for “lexical semantics”

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.

9 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS2013

V and V of Lexical, Syntactic and Semantic Properties for Interactive Systems Through Model Checking of Formal Description of Dialog

During early phases of the development of an interactive system, future system properties are identified (through interaction with end users in the brainstorming and prototyping phase of the application, or by other stakehold-ers) imposing requirements on the final system. They can be specific to the application under development or generic to all applications such as usability principles. Instances of specific properties include visibility of the aircraft altitude, speed… in the cockpit and the continuous possibility of disengaging the autopilot in whatever state the aircraft is. Instances of generic properties include availability of undo (for undoable functions) and availability of a progression bar for functions lasting more than four seconds. While behavioral models of interactive systems using formal description techniques provide complete and unambiguous descriptions of states and state changes, it does not provide explicit representation of the absence or presence of properties. Assessing that the system that has been built is the right system remains a challenge usually met through extensive use and acceptance tests. By the explicit representation of properties and the availability of tools to support checking these properties, it becomes possible to provide developers with means for systematic exploration of the behavioral models and assessment of the presence or absence of these properties. This paper proposes the synergistic use two tools for checking both generic and specific properties of interactive applications: Petshop and Java PathFinder. Petshop is dedicated to the description of interactive system behavior. Java PathFinder is dedicated to the runtime verification of Java applications and as an extension dedicated to User Interfaces. This approach is exemplified on a safety critical application in the area of interactive cockpits for large civil aircrafts.

human-computer interface↗
DOE OSTI2025

Replacing non-biomedical concepts improves embedding of biomedical concepts

Embeddings are semantically meaningful representations of words in a vector space, commonly used to enhance downstream machine learning applications. Traditional biomedical embedding techniques often replace all synonymous words representing biological or medical concepts with a unique token, ensuring consistent representation and improving embedding quality. However, the potential impact of replacing non-biomedical concept synonyms has received less attention. Embedding approaches often employ concept replacement to replace concepts that span multiple words, such as non-small-cell lung carcinoma, with a single concept identifier (e.g., D002289). Also, all synonyms of each concept are merged into the same identifier. Here, we additionally leveraged WordNet to identify and replace sets of non-biomedical synonyms with their most common representatives. This combined approach aimed to reduce embedding noise from non-biomedical terms while preserving the integrity of biomedical concept representations. We applied this method to 1,055 biomedical concept sets representing molecular signatures or medical categories and assessed the mean pairwise distance of embeddings with and without non-biomedical synonym replacement. A smaller mean pairwise distance was interpreted as greater intra-cluster coherence and higher embedding quality. Embeddings were generated using the Word2Vec algorithm applied to a corpus of 10 million PubMed abstracts. Our results demonstrate that the addition of non-biomedical synonym replacement reduced the mean intra-cluster distance by an average of 8%, suggesting that this complementary approach enhances embedding quality. Future work will assess its applicability to other embedding techniques and downstream tasks. Python code implementing this method is provided under an open-source license.

algorithms↗
DOE OSTI2024

chatHPC: Empowering HPC users with large language models

The ever-growing number of pre-trained large language models (LLMs) across scientific domains presents a challenge for application developers. While these models offer vast potential, fine-tuning them with custom data, aligning them for specific tasks, and evaluating their performance remain crucial steps for effective utilization. However, applying these techniques to models with tens of billions of parameters can take days or even weeks on modern workstations, making the cumulative cost of model comparison and evaluation a significant barrier to LLM-based application development. To address this challenge, we introduce an end-to-end pipeline specifically designed for building conversational and programmable AI agents on high performance computing (HPC) platforms. Our comprehensive pipeline encompasses: model pre-training, fine-tuning, web and API service deployment, along with crucial evaluations for lexical coherence, semantic accuracy, hallucination detection, and privacy considerations. Here, we demonstrate our pipeline through the development of chatHPC, a chatbot for HPC question answering and script generation. Leveraging our scalable pipeline, we achieve end-to-end LLM alignment in under an hour on the Frontier supercomputer. We propose a novel self-improved, self-instruction method for instruction set generation, investigate scaling and fine-tuning strategies, and conduct a systematic evaluation of model performance. The established practices within chatHPC will serve as a valuable guidance for future LLM-based application development on HPC platforms.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1983

Top-down methodology for human factors research

User computer interaction as a conversation is discussed. The design of user interfaces which depends on viewing communications between a user and the computer as a conversion is presented. This conversation includes inputs to the computer (outputs from the user), outputs from the computer (inputs to the user), and the sequencing in both time and space of those outputs and inputs. The conversation is viewed from the user's side of the conversation. Two languages are modeled: the one with which the user communicates with the computer and the language where communication flows from the computer to the user. Both languages exist on three levels; the semantic, syntactic and lexical. It is suggested that natural languages can also be considered in these terms.

Sibert, J.↗
NASA NTRS1977

A survey of compiler development aids

A theoretical background was established for the compilation process by dividing it into five phases and explaining the concepts and algorithms that underpin each. The five selected phases were lexical analysis, syntax analysis, semantic analysis, optimization, and code generation. Graph theoretical optimization techniques were presented, and approaches to code generation were described for both one-pass and multipass compilation environments. Following the initial tutorial sections, more than 20 tools that were developed to aid in the process of writing compilers were surveyed. Eight of the more recent compiler development aids were selected for special attention - SIMCMP/STAGE2, LANG-PAK, COGENT, XPL, AED, CWIC, LIS, and JOCIT. The impact of compiler development aids were assessed some of their shortcomings and some of the areas of research currently in progress were inspected.

Buckles, B. P.↗
DOE OSTI2020

A Computational Theory for the Emergence of Grammatical Categories in Cortical Dynamics

A general agreement in psycholinguistics claims that syntax and meaning are unified precisely and very quickly during online sentence processing. Although several theories have advanced arguments regarding the neurocomputational bases of this phenomenon, we argue that these theories could potentially benefit by including neurophysiological data concerning cortical dynamics constraints in brain tissue. In addition, some theories promote the integration of complex optimization methods in neural tissue. In this paper we attempt to fill these gaps introducing a computational model inspired in the dynamics of cortical tissue. In our modeling approach, proximal afferent dendrites produce stochastic cellular activations, while distal dendritic branches–on the other hand–contribute independently to somatic depolarization by means of dendritic spikes, and finally, prediction failures produce massive firing events preventing formation of sparse distributed representations. The model presented in this paper combines semantic and coarse-grained syntactic constraints for each word in a sentence context until grammatically related word function discrimination emerges spontaneously by the sole correlation of lexical information from different sources without applying complex optimization methods. By means of support vector machine techniques, we show that the sparse activation features returned by our approach are well suited—bootstrapping from the features returned by Word Embedding mechanisms—to accomplish grammatical function classification of individual words in a sentence. In this way we develop a biologically guided computational explanation for linguistically relevant unification processes in cortex which connects psycholinguistics to neurobiological accounts of language. We also claim that the computational hypotheses established in this research could foster future work on biologically-inspired learning algorithms for natural language processing applications.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS1997

Computer Supported Indexing: A History and Evaluation of NASA's MAI System

Computer supported indexing systems may be categorized in several ways. One classification scheme refers to them as statistical, syntactic, semantic or knowledge-based. While a system may emphasize one of these aspects, most systems actually combine two or more of these mechanisms to maximize system efficiency. Statistical systems can be based on counts of words or word stems, statistical association, and correlation techniques that assign weights to word locations or provide lexical disambiguation, calculations regarding the likelihood of word co-occurrences, clustering of word stems and transformations, or any other computational method used to identify pertinent terms. If words are counted, the ones of median frequency become candidate index terms. Syntactical systems stress grammar and identify parts of speech. Concepts found in designated grammatical combinations, such as noun phrases, generate the suggested terms. Semantic systems are concerned with the context sensitivity of words in text. The primary goal of this type of indexing is to identify without regard to syntax the subject matter and the context-bearing words in the text being indexed. Knowledge-based systems provide a conceptual network that goes past thesaurus or equivalent relationships to knowing (e.g., in the National Library of Medicine (NLM) system) that because the tibia is part of the leg, a document relating to injuries to the tibia should he indexed to LEG INJURIES, not the broader MeSH term INJURIES, or knowing that the term FEMALE should automatically be added when the term PREGNANCY is assigned, and also that the indexer should be prompted to add either HUMAN or ANIMAL. Another way of categorizing indexing systems is to identify them as producing either assigned- or derived-term indexes.

Silvester, June P.↗
DOE OSTI2025

BuildingQA: A Benchmark for Natural Language Question Answering over Building Knowledge Graphs

Graph-based representations of building metadata using ontologies like Brick are vital for smart building applications, but querying them remains a challenge for practitioners. Knowledge Graph Question Answering (KGQA) systems, meant to retrieve answers from natural language questions, traditionally require large-scale training data, making them ill-suited for the specialized and data-scarce building domain. The advent of Large Language Models (LLMs) offers a paradigm shift, enabling zero-shot natural language querying without building/domain-specific training. Yet, there is no standardized benchmark for building-specific KGQA which can guide and validate research in this area. To address this gap, our work makes three primary contributions. First, we introduce the BuildingQA Benchmark Dataset, constructed through a multi-stage process of collecting practitioner data, augmenting it with LLMs for linguistic diversity, and curating a final set of 188 questions across 4 buildings. Second, we characterize the benchmark's complexity and ambiguity, introducing a novel method to quantify its "lexical gap" and providing a four-stage diagnostic framework for analyzing how systems fail. Third, we benchmark zero-shot LLM-powered KGQA systems to establish baseline performance and analyze their failure modes. Our evaluation reveals that top-performing systems achieve a maximum F1 score of only 0.38. This result does not indicate a failure of these powerful systems, but rather underscores the unique challenges posed by our benchmark. It demonstrates a critical performance gap, showing that current methods successful on general KGs struggle with the specific lexical and structural nuances of the building domain. BuildingQA1 thus provides the benchmark dataset and foundational analysis needed to drive the development of novel, domain-aware methods required to unlock the use of semantic data in buildings.

Mulayim, Ozan Baris↗
NASA NTRS2000

A dual-task investigation of automaticity in visual word processing

An analysis of activation models of visual word processing suggests that frequency-sensitive forms of lexical processing should proceed normally while unattended. This hypothesis was tested by having participants perform a speeded pitch discrimination task followed by lexical decisions or word naming. As the stimulus onset asynchrony between the tasks was reduced, lexical-decision and naming latencies increased dramatically. Word-frequency effects were additive with the increase, indicating that frequency-sensitive processing was subject to postponement while attention was devoted to the other task. Either (a) the same neural hardware shares responsibility for lexical processing and central stages of choice reaction time task processing and cannot perform both computations simultaneously, or (b) lexical processing is blocked in order to optimize performance on the pitch discrimination task. Either way, word processing is not as automatic as activation models suggest.

Attention↗