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 7 of 7 for “"Word Similarity"”.
-
Eliminating Redundant and Less-informative RSS News Articles Based on Word Similarity and A Fuzzy Equivalence Relation
… aggregators. Our filtering approach measures similarity among RSS news entries by using the Fuzzy-Set Information Retrieval model and a fuzzy equivalent relation for computing word/sentence similarity to detect redundant and less-informative news articles.
-
Three explanations for the link between language style matching and liking
… style is defined by his or her use of function words (e.g., pronouns, articles), a class of short, commonly used words that make up the grammatical structure of language. The language style matching (LSM) metric indexes the degree of similarity between two individual’s patterns of function word …
-
AWE: Attention Word Embedding
Word embedding models learn semantically rich vector representations of words and are widely used to initialize natural processing language (NLP) models. The popular continuous bag-of-words (CBOW) model of word2vec learns a vector embedding by masking a given word in a sentence and then using the …
-
Concept and entity grounding using indirect supervision
… non-English names into English, and computing word similarity across languages. Since it is impossible to acquire manually annotated examples for all languages, building models for all languages in Wikipedia requires exploring indirect or incidental supervision signals which already exist in …
-
Representation Learning beyond Semantic Similarity: Character-aware and Function-specific Approaches
… consequently encodes general information about word similarity. Words or phrases with similar meaning obtain similar representations in a vector space constructed for this purpose. This established methodology excels for morphologically-simple languages such as English, and in data-rich …
-
Expressions of psychological stress on Twitter: detection and characterisation
… and relaxation scores in social media. Using a word-vector based word sense disambiguation method, the TensiStrength lexicon was modified to include the stress scores of the different senses of the same word. On a dataset of 1000 tweets containing ambiguous stress-related words, the accuracy of …
-
Lexical entailment
… those that make use of knowledge bases such as WordNet. Interestingly, these methods make very different kinds of mistakes and so in this thesis, we construct a new entailment measure by combining these two paradigms in such a way that exploits their differences. We also experiment with …