Sökning: "Graph Similarity"

Visar resultat 1 - 5 av 18 avhandlingar innehållade orden Graph Similarity.

  1. 1. Best Trees Extraction and Contextual Grammars for Language Processing

    Författare :Anna Jonsson; Johanna Björklund; Frank Drewes; Hendrik Jan Hoogeboom; Umeå universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Weighted tree automata; the N-best problem; efficient algorithms; semantic graph; abstract meaning representation; contextual graph grammars; hyperedge replacement; graph extensions;

    Sammanfattning : In natural language processing, the syntax of a sentence refers to the words used in the sentence, their grammatical role, and their order. Semantics concerns the concepts represented by the words in the sentence and their relations, i.e., the meaning of the sentence. LÄS MER

  3. 2. Mobility Knowledge Graph and its Application in Public Transport

    Författare :Qi Zhang; Zhenliang Ma; Erik Jenelius; Carlos Lima Azevedo; KTH; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Knowledge graph; Smart card data; Public transport; User-station attention; Relation extraction; Transportvetenskap; Transport Science; Transportsystem; Transport Systems;

    Sammanfattning : Efficient public transport planning, operations, and control rely on a deep understanding of human mobility in urban areas. The availability of extensive and diverse mobility data sources, such as smart card data and GPS data, provides opportunities to quantitatively study individual behavior and collective mobility patterns. LÄS MER

  4. 3. Scalable Machine Learning through Approximation and Distributed Computing

    Författare :Theodore Vasiloudis; Anders Holst; Henrik Boström; Seif Haridi; Daniel Gillblad; Indre Žliobaitė; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Online Learning; Distributed Computing; Graph Similarity; Decision Trees; Gradient Boosting;

    Sammanfattning : Machine learning algorithms are now being deployed in practically all areas of our lives. Part of this success can be attributed to the ability to learn complex representations from massive datasets. LÄS MER

  5. 4. Global geometric graph kernels and applications

    Författare :Fredrik Johansson; Chalmers tekniska högskola; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES;

    Sammanfattning : This thesis explores the topics of graph kernels and classification of graphs. Graph kernels have received considerable attention in the last decade, in part because of their value in many practical applications, such as chemo informatics and molecular biology, in which classification using graph kernels have become the standard model for several problems. LÄS MER

  7. 5. Graph Algorithms for Large-Scale and Dynamic Natural Language Processing

    Författare :Kambiz Ghoorchian; Magnus Boman; Magnus Sahlgren; Sumithra Velupillai; KTH; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Natural Language Processing; Lexical Disambiguation; Topic Modeling; Representation Learning; Graph Partitioning; Distributed Algorithms; Dimensionality Reduction; Random Indexing; ;

    Sammanfattning : In Natural Language Processing, researchers design and develop algorithms to enable machines to understand and analyze human language. These algorithms benefit multiple downstream applications including sentiment analysis, automatic translation, automatic question answering, and text summarization. LÄS MER