Search Results

Search Constraints

Start Over
Filtering by: Discipline Engineering Remove constraint Discipline: Engineering Discipline Other Remove constraint Discipline: Other

Search Results

  • Enhanced word embeddings using multi-semantic representation through lexical chains

    work
    Creator:
    Ruas, Terry, Ferreira, Charles H. P., Grosky, William, França, Fabrício O., and Medeiros, Débora M. R,
    Description:
    The relationship between words in a sentence often tell us more about the underlying semantic content of a document than its actual words, individually. Recent publications in the natural language processing arena, more specifically using word embeddings, try to incorporate semantic aspects into their word vector representation by considering the context of words and how they are distributed in a document collection. In this work, we propose two novel algorithms, called Flexible Lexical Chain II and Fixed Lexical Chain II that combine the semantic relations derived from lexical chains, prior knowledge from lexical databases, and the robustness of the distributional hypothesis in word embeddings into a single decoupled system. In short, our approach has three main contributions: (i) unsupervised techniques that fully integrate word embeddings and lexical chains; (ii) a more solid semantic representation that considers the latent relation between words in a document; and (iii) lightweight word embeddings models that can be extended to any natural language task. Knowledge-based systems that use natural language text can benefit from our approach to mitigate ambiguous semantic representations provided by traditional statistical approaches. The proposed techniques are tested against seven word embeddings algorithms using five different machine learning classifiers over six scenarios in the document classification task. Our results show that the integration between lexical chains and word embeddings representations sustain state-of-the-art results, even against more complex systems. Github:  https://github.com/truas/LexicalChain_Builder
    Keyword:
    document classification, lexical chains, word embeddings, synset embeddings, chain2vec, and natural language processing
    Citation to related publication:
    Terry Ruas, Charles Henrique Porto Ferreira, William Grosky, Fabrício Olivetti de França, Débora Maria Rossi de Medeiros, "Enhanced word embeddings using multi-semantic representation through lexical chains", Information Sciences, 2020,  https://doi.org/10.1016/j.ins.2020.04.048
    Discipline:
    Other, Science, and Engineering

  • A Simulated Wind-field Dataset for Testing Energy Efficient Path-Planning Algorithms for UAVs in Urban Environment

    work
    Creator:
    Baskar, Deepika and Gorodetsky, Alex
    Description:
    Studying the effect of wind on urban air mobility typically requires comprehensive fluid dynamics simulations in a realistic urban geometry. Motivated to enable wide-spread autonomous drone activity in urban centers, such studies have indeed been considered by several authors in the recent literature. However, the accessibility of these approaches to those with less fluid dynamics experience and/or without access to purpose built simulation tools has limited validation and application of the resulting path planning strategies. and The .dat files contain the flow variables for each of the 402240 points sampled from the region under study. For flow visualization purposes, the .dat files are readable using Tecplot Software.
    Keyword:
    UAM, Energy efficient path planning , CFD, and City of Boston
    Citation to related publication:
    Baskar, D., & Gorodetsky, A. (2020). A Simulated Wind-field Dataset for Testing Energy Efficient Path-Planning Algorithms for UAVs in Urban Environment. In AIAA AVIATION 2020 FORUM. American Institute of Aeronautics and Astronautics.  https://doi.org/10.2514/6.2020-2920
    Discipline:
    Other and Engineering

  • Downloaded IAAF Sprint Results in all Heats for 2004 - 2016 Olympics for both Men and Women

    work
    Creator:
    Mirshams Shahshahani, Payam
    Description:
    Investigating minimum human reaction times is often confounded by the motivation, training, and state of arousal of the subjects. We used the reaction times of athletes competing in the shorter sprint events in the Athletics competitions in recent Olympics (2004-2016) to determine minimum human reaction times because there's little question as to their motivation, training, or state of arousal. The reaction times of sprinters however are only available on the IAAF web page for each individual heat, in each event, at each Olympic. Therefore we compiled all these data into two separate excel sheets which can be used for further analyses.
    Keyword:
    minimum reaction time, sprinter, Olympics, Athletics, sex difference, starting block, and false start
    Discipline:
    Engineering, Health Sciences, Science, Other, and General Information Sources