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 20 of 43 for “"word embedding"”.
-
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 …
-
Post-processing Techniques for Word Embedding
Word embedding has been a significant breakthrough in natural language processing (NLP). Although word representation has improved remarkably and resulted in better performance in downstream NLP applications, interpretability of word embeddings remains a challenge. Post-processing techniques have …
-
Text mining with word embedding for outlier and sentiment analysis
… text mining tools to analyze massive text data. Word embedding is an emerging text analysis technique that leverages the fine-grained statistics of context information to map each word to a vector in the embedding space which reflects the semantic proximity between words. Embedding techniques not …
-
Addressing Semantic Interoperability and Text Annotations. Concerns in Electronic Health Records using Word Embedding, Ontology and Analogy
… another consideration was the use of word embedding and ontology for knowledge discovery. In medical domain, the main challenge for medical information extraction system is to find the required information by considering explicit and implicit clinical context with high degree of …
-
An unsupervised approach to COVID-19 fake tweet detection
… of Twitter data in the two of clusters. Word embedding techniques such as TF-IDF, Word2Vec, and BERT were employed because machine learning models cannot process unprocessed text data directly, and word embedding resolves this issue. Results: The results on the test data show that K-means …
-
Geometry of compositionality
Word embedding is a popular representation of words in vector space, and its geometry reveals the lexical semantics. This thesis further explores the interesting geometric properties of word embedding, and looks into its interaction with the context representation. We propose an innovative method …
-
NON - RELIGIOUS DISCOURSES AND THE SECULARIZATION OF THE SECULAR: A COMPUTATIONAL STUDY OF ORGANIZED NON - RELIGION IN THE UNITED STATES AND THE UNITED KINGDOM (1881-2019).
… Modeling all'Analisi del Sentiment e al Dynamic Word Embedding, per esplorare una vasta raccolta di riviste pubblicate da due organizzazioni non-religiose americane e due britanniche tra il 1881 e il 2019. L'analisi rivela che le fluttuazioni storiche nella rilevanza attribuita alla religione da …
-
Modeling Similarities Among Autism Spectrum Patients Using Word Embeddings on Clinical Notes
… they present. We used Doc2Vec to create neural word embedding vectors on the clinical notes presented and K-means clustering to group the patients based on similarities in the notes. The clusters will give us greater insight into the examinations done by clinicians in ABA therapy, the …
-
Embedding and latent variable models using maximal correlation
… conditional expectation algorithm to construct embeddings one dimensional at a time to maximally preserve the linear correlation in the embedding space. Each dimension is enforced to be orthogonal to all other dimensions to not encode redundant information. Intuitively, we want to map objects …
-
Neural Networks for Music Emotion Recognition and Social Tags Emotion Representation
… related to music emotion by utilizing neural word embedding approaches. This way, social tags could be mapped into the dimensional emotion plane for further quantitative use. To conclude, my research aims to improve the performance of music emotion recognition with neural network methods and …
-
Unified processing of natural language and relational data
… database and its extensibility to allow for word embedding without leaving the relational database. This system can be extended to incorporate several natural language processing (NLP) techniques, such as latent Dirichlet allocations(LDA) or modern models, such as BERT. The combination of NLP …
-
Improving the accuracy and diversity of feature extraction from online reviews using keyword embedding and two clustering methods
… data. Among them, this thesis focused on the word embedding and clustering which is an automated feature extraction method using online product review data. The methodology does identify product features but has some limits. The research presented in this thesis addresses those limitations and …
-
Conditional Neural Language Models for Multimodal Learning and Natural Language Understanding
… a LSTM encoder for learning visual-semantic embeddings for ranking the relevance of text to images in a joint embedding space. Next we introduce three log-bilinear models for generating image descriptions that integrate both additive and multiplicative interactions. Beyond image conditioning, …
-
Software Requirements Classification Using Word Embeddings and Convolutional Neural Networks
… classification, specifically the use of word embeddings for document representation when training a convolutional neural network (CNN). As past research endeavors mainly utilize information retrieval and traditional machine learning techniques, we entertain the potential of deep learning …
-
Enriching Word Representation Learning for Affect Detection and Affect-Aware Recommendations
… to improve affect detection in text by enhancing word representation learning. We enrich word representations in two ways: one by effective pre-processing of training word embeddings and second by incorporating both affective and contextual features deeply into text representations. We demonstrate …
-
Mid-level representations for action recognition and zero-shot learning
… the third problem, we observe that distributed word embeddings, which become a popular mid-level representation for zero-shot learning due to their easy accessibility, are designed to reflect semantic similarity rather than visual similarity and thus using them in zero-shot learning often leads …
-
INCORPORATING EMR AND GENOMIC DATA USING NLP AND MACHINE LEARNING TO REFINE CANCER TREATMENT
… performance among RNNs. In addition, pre-trained word embedding can improve the results of RNNs and reduce their training time. Our findings demonstrated that RNN-based algorithms have advantages in unstructured clinical progress reports classification.
-
Exploring embedding vectors for emotion detection
… Many approaches have been based on the emotional words or lexicons in order to detect emotions. While the word embedding vectors like Word2Vec have been successfully employed in many NLP approaches, the word mover’s distance (WMD) is a method introduced recently to calculate the distance between …
-
Classification of customer complaints using machine learning algorithms
… These algorithms are trained on three different word vectorisation techniques namely: CV, TFIDF, and Word2Vec word-embedding. The algorithms are meant to classify each customer complaint into one of the thirteen possible Products. Due to imbalanced distributions of the target (Product complaint …
-
Exploiting Semantic Similarity Between Citation Contexts For Direct Citation Weighting And Residual Citation
… contexts were obtained using BioSent2Vec word-embedding model for biomedical publications. The residual citation aspect sample included ten base articles and five generations of citations from which 5272 citation context pairs were obtained. Results of the Spearman’s rank correlation test …
Page 1 of 3