Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 14 of 14 for “"Pointwise Mutual Information"”.

  1. Počítač jako inteligentní spoluhráč ve slovně-asociační hře Krycí jména

    … modelu fastText a metody založené na počtu Pointwise Mutual Information. Je zde popsán systém, který s využitím sémantických modelů je schopen zastoupit hráče ve slovně-asociační hře Krycí jména. Systém má implementovanou herní strategii využívající informace z průběhu hry k prospěchu týmu, …

    brno-tech Repository record for Počítač jako inteligentní spoluhráč ve slovně-asociační hře Krycí jména (opens in a new tab)

  2. Rychlá adaptace počítačové podpory hry Krycí jména pro nové jazyky

    … kde nejlepších výsledků dosahovala metoda Pointwise Mutual Information a prediktivní model fastText. Systém podporuje hraní Krycích jmen v 36 jazycích tvořených 8 různými abecedami.

    brno-tech Repository record for Rychlá adaptace počítačové podpory hry Krycí jména pro nové jazyky (opens in a new tab)

  3. Počítač jako inteligentní spoluhráč ve slovně-asociační hře Krycí jména

    … s metodou DETECT, a model založený na výpočtu Pointwise Mutual Information. Metoda DETECT využívá model Dict2vec, který je trénován na slovníkových definicích pojmů. Výsledný systém je schopen zastoupit hráče při hraní slovně asociační hry Krycí jména, a to jak na pozici člena operativy, tak v …

    brno-tech Repository record for Počítač jako inteligentní spoluhráč ve slovně-asociační hře Krycí jména (opens in a new tab)

  4. Quantitative Approaches to the Study of Russian Dialects

    … frequency-based analysis with Normalized Pointwise Mutual Information (nPMI). The results confirm major established distinctions in Russian dialectology, particularly the opposition between Northern and Southern dialects, while also providing novel results on the specific features …

    cau-kiel Repository record for Quantitative Approaches to the Study of Russian Dialects (opens in a new tab)

  5. Leveraging keyword identification for abusive language detection in social online domains

    … that identifies and removes non-keywords using pointwise mutual information to address linguistic challenges such as domain-specific language and misspelled words. This process emphasizes the remaining words and builds a stronger association between word-category pairs. We also explore an online …

    bu Repository record for Leveraging keyword identification for abusive language detection in social online domains (opens in a new tab)

  6. Applications of corpus-based semantic similarity and word segmentation to database schema matching

    … methods. Our word similarity method uses Pointwise Mutual Information (PMI) to sort lists of important neighbor words of the two target words and distinguish the words which are common in both lists and aggregate their PMI values (from the opposite list) to calculate the relative …

    ottawa-retro Repository record for Applications of corpus-based semantic similarity and word segmentation to database schema matching (opens in a new tab)

  7. CASSANDRA: drug gene association prediction via text mining and ontologies

    … complex drug mechanisms, and extract relation information that can support computational polypharmacology. In this work, we introduce CASSANDRA, a fully corpus-based and unsupervised algorithm which uses the MEDLINE indexed titles and abstracts to infer drug gene associations and assist drug …

    qucosa-diss

  8. Unsupervised concept extraction in an introductory programming course

    … text documents, including the code structure information. First, we projected, implemented, and deployed a learning environment based on a teaching methodology to collect professors and student data. Then, we extracted the underlying relationship between questions and validated the results …

    brazil-uerj Repository record for Unsupervised concept extraction in an introductory programming course (opens in a new tab)

  9. Information-Theoretic Approaches to Curating and Analyzing Geoscientific Text: A Case Study using the xDD Database

    … relationships from geoscientific texts using information-theoretic metrics. Drawing on a corpus derived from the xDD Snippet API, over 12 million unique text excerpts were retrieved and processed for 1,094 geological search terms. A reproducible pipeline was developed to tokenize, normalize, …

    sask Repository record for Information-Theoretic Approaches to Curating and Analyzing Geoscientific Text: A Case Study using the xDD Database (opens in a new tab)

  10. The Role of negative information when learning dense word vectors

    … that this vector captures semantic and syntactic information. Word embeddings derived from unannotated corpora can be divided into (1) counting methods which perform factorization of the word-context cooccurrence matrix and (2) predictive methods where neural networks are trained to predict word …

    brazil-ufrgs Repository record for The Role of negative information when learning dense word vectors (opens in a new tab)

  11. Domain-Specific Senitment Analysis of Historical Australian Parliamentary Speeches

    … obtain historically. Unsupervised methods infer information directly from a large corpus of texts. We focused on using distributional unsupervised methods to construct a domain-specific sentiment dictionary for historical Australian parliamentary speeches. This requires constructing a …

    adelaide Repository record for Domain-Specific Senitment Analysis of Historical Australian Parliamentary Speeches (opens in a new tab)

  12. Streaming and Sketch Algorithms for Large Data NLP

    … computing approximate association scores like pointwise mutual information (PMI), finding frequent items (like n-grams), building streaming language models, and measuring distributional similarity. First, I introduce the concept of approximate streaming large-scale language models in NLP. …

    maryland Repository record for Streaming and Sketch Algorithms for Large Data NLP (opens in a new tab)

  13. Context-Based Personalisation in Neural Machine Translation of Dialogue

    … sentences, disregarding crucial contextual information in the process. This lack of context awareness frequently leads to assumptions about the most likely interpretation of the source text, potentially propagating harmful biases learned from the training data, such as assuming that the …

    whiterose Download PDF for Context-Based Personalisation in Neural Machine Translation of Dialogue (opens in a new tab)

  14. Word meaning in context as a paraphrase distribution : evidence, learning, and inference

    … word. To encode the fact that lexical semantic information is exchanged between syntactic neighbors, the graph contains edges that mirror the dependency graph for the sentence. Further knowledge sources that influence the hidden nodes are represented through additional edges that, for example, …

    texas Repository record for Word meaning in context as a paraphrase distribution : evidence, learning, and inference (opens in a new tab)