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 30 for “"Topic Classification"”.
-
Relation-ontology drive topic classification
Conventional topic models have been extensively used to extract topics in documents for topic classification. For example, Latent Dirichlet Allocation (LDA) is a topic modelling technique that produces a probabilistic model based on word co-occurrence, for the purpose of text classification. …
-
Deep Learning Models for Topic Classification and Disentanglement
Modeling topics discussed in texts is a fundamental problem in natural language processing, which includes specific tasks in topic classification, clustering, and disentanglement. The capability of machines in understanding and modeling topics is a key component needed for developing many natural …
-
Discriminative and adaptive training for robust speech recognition and understanding
… objectives are proposed for keyword spotting and topic classification: (1) To accurately recognize the semantically important keywords, the non-uniform error cost minimum classification error training of deep neural network (DNN) and bi-directional long short-term memory (BLSTM) acoustic models is …
-
Deep neural networks for information mining from legal texts
… (Mencia, 2009; Hasan et al., 2008), legal topic classification (Mencia and Fürnkranzand, 2007; Nallapati and Manning, 2008), legal judgment prediction and analysis (Wang et al., 2012; Aletras et al., 2016), legal information extraction (Kiyavitskaya et al., 2008; Dozier et al., 2010; Asooja …
-
An Evaluation of Text Classification Methods for Literary Study
… are consistent with what are obtained in topic classification, such as Odds Ratio does not improve SVM performance and stop word removal might harm classification. Some conclusions contradict previous results, such as SVM does not beat naive Bayes in both cases. Some findings are new to …
-
CONTROLLABLE NEURAL RETRIEVAL THROUGH STRUCTURED REPRESENTATIONS
… interpretable structure for tasks including topic classification and political bias detection. Third, explicit value targets and activation subspaces structure value-conditioned response retrieval, revealing and mitigating gradient interference between conflicting values while enabling …
-
Diverse dataset synthesis using retrieval augmented language models
… smaller student models. One way to do this for classification tasks is via dataset synthesis, which can be accomplished by generating examples of each label from the LLM. Prior approaches to synthesis use few-shot prompting, which relies on the LLM's parametric knowledge to generate usable …
-
Learning from Multi-Source Weak Supervision for Neural Text Classification
Text classification is a fundamental text mining task with numerous real-life applications. While deep neural nets have achieved superior performance for text classification, they rely on large-scale labeled data to achieve strong performance. Obtaining large-scale labeled data, however, can be …
-
The relevance of information systems (IS) research publications to IS practitioners' key concerns
… research was to determine if, and if so how, the topics published in information systems (IS) journal articles were related to the key issues reported to be of concern to IS managers. The secondary aim was to determine what proportions of the journal articles were investigating closely-related and …
-
An intelligent class : the development of a novel context capturing method for the functional auto-classification of records
… core problem in many domains. Historically, the classification of records was done manually as records were received and then categorized. Unfortunately, due to a significant growth in the volume of records, the need for robust auto-classification methods that can effectively “read” and classify …
-
Applications of Stochastic Gradient Descent to Nonnegative Matrix Factorization
… recognition, we show that our approach produces classification performance competitive with existing matrix factorization algorithms. In the second application, document topic classification, we examine how well SGD can recover an unknown words-to-topics matrix when the topics-to-document matrix …
-
Evolution of Blockchain Technology: Dynamics of Knowledge Flow and Thematic Trends
… incorporating various methodologies such as LDA topic modeling, citation network analysis, and main path analysis. The categorization of blockchain technology into topics was conducted using the LDA machine learning model, which can provide more objective and robust topic classification than …
-
Semi-Supervised Learning For Identifying Opinions In Web Content
… for detecting personal attitudes regarding topics, products, and services. The opinion detection literature indicates that both a large body of opinions and a wide variety of opinion features are essential for capturing subtle opinion information. Although a large amount of opinion-labeled …
-
Modeling phones, keywords, topics and intents in spoken languages
… language components such as phones, keywords, topics and intents during both human/machine interactions and human/human communications. Eventually, if we can develop a machine assistant for people to understand the basic meaning of any language in speech, we could make the human world much more …
-
Essays on applications of text analysis in macroeconomics
… changes in communication bandwidth across topics using large-language-model probabilistic topic classification. Using an event-study approach, I find that increased discussion of monetary policy tools (economic conditions) is associated with an increase (decrease) in the variation of …
-
Scaling up Labeling, Mining, and Inferencing on Event Extraction
… up event extraction by using the document topics information in a topic-aware deep learning framework. We propose a domain-aware event extraction method by using the topic name embeddings to enrich the sentences' contextual representations and multi-task setup of event extraction and topic …
-
Statistical Issues in Quantifying Text Mining Performance
… more complicated than analyzing numerical data. Topic modeling is a commonly-used approach to classify text documents into topics and identify key words, so the text information of interest is distilled from the large corpus sea. In this dissertation, I investigate various statistical issues in …
-
Topic-enhanced Models for Speech Recognition and Retrieval
This thesis aims to examine ways in which topical information can be used to improve recognition and retrieval of spoken documents. We consider the interrelated concepts of locality, repetition, and `subject of discourse' in the context of speech processing applications: speech recognition, speech …
-
A study of Rwanda’s two-way text messaging support for isolated COVID-19 patients during the pandemic : patient use and AI-enhanced conversation analysis
… English-translated (as necessary), topic-labelled, language-restored, and used to train single-topic classifiers (Traditional-ML/Transformer architectures). Best-performing models meeting a F1≥0.7 cutoff were applied to unlabeled conversations. Topic prevalence and sociodemographic …
Page 1 of 2