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 “"low-resource languages"”.
-
Unsupervised speech technology for low-resource languages
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms
-
Unsupervised speech technology for low-resource languages
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms
-
Improving Parameter-Efficient Cross-Lingual Transfer for Low-Resource Languages
… imperative to develop such models in different languages. This endeavour aims to enable access to emerging technologies to a broad spectrum of individuals, irrespective of their language. The most challenging scenario is arguably that of low-resource languages, often lacking labelled data while …
-
Echolocation: Using Word-Burst Analysis to Rescore Keyword Search Candidates in Low-Resource Languages
… are very accurate for heavily studied languages like English. They perform poorly, though, for languages wherein the recorded archives of speech data available to researchers are relatively scant. In the context of these low-resource languages, the task of keyword search within recorded …
-
Consonant (De)gradation in Ingrian?
… present a dual method toward data enrichment for low-resource languages. Using Yoyodyne -- a Fairseq-inspired neural library for small-vocabulary sequence-to-sequence generation -- a morphological generation task was tested across labeled data encompassing multiple stages of enrichment for the …
-
Improving Low-Resource Translation with Finite State Grammars
… of neural machine translation systems for low-resource languages. This study develops a method for the incorporation of linguistic information into the training of neural machine translation models for low-resource languages, using morphological grammars created using finite state …
-
Crosslingual Sharing for Low-Resource Natural Language Processing
… However, these techniques rely on resources, such as extensive task-specific annotation and vast amounts of unlabeled text, which are not available in every language. Thus, most prior research has been focused on high-resource languages such as English. Crosslingual transfer from a …
-
Cold-start universal information extraction
… unstructured data from various sources, such as languages, genres and domains. When building an IE system, the conventional pipeline is to (1) ask expert linguists to rigorously define a target set of knowledge types we wish to extract by examining a large data set, (2) collect resources and …
-
Acoustic event, spoken keyword and emotional outburst detection
… cross-lingual keyword spotting to support low resource languages and finds that the acoustic model is dominant in determining the cross-lingual keyword search performance. Third, the thesis further presents the emotional outburst detection for infant nonspeech acoustic events. It reports on …
-
Evaluating automated and hybrid neural disambiguation for African historical named entities
… have shown the ability to learn concepts across languages, reducing the amount of training data required in low-resource languages. Thus a multilingual language model-based NED system was developed to disambiguate people's names within a historical South African context using documents written in …
-
Towards Large Language Models for Everyone: Instruction Following, Knowledge Retrieval and Multilingualism
… and few-shot generalization across medium- and low-resource languages. Together, these research strands provide core strategies for advancing the boundaries of LLM capabilities and paving the way towards real-world deployment.
-
Exploring neural network architectures for acoustic modeling
… and environment variability, especially under low-resource, distant microphone, noisy, and reverberant conditions. The goal of this thesis is to explore novel neural architectures that can effectively improve ASR performance. In the first part of the thesis, we present a well-engineered, …
-
A Study on Neural-based Code Summarization in Low-resource Settings
… to its application in novel programming languages where only a few well-documented programs in these low-resource languages are available for training. According to our observation, existing approaches can only acquire poor performances in such settings, and we attribute the problem to …
-
Modeling phones, keywords, topics and intents in spoken languages
Spoken Language Understanding for both rich-resource languages (RRL) and low-resource languages (LRL) is an important research area for academia and the commercial world. In the conversational situations where either the language used in speech is a minority one, or the environment is noisy, …
-
On the Evaluation and Modelling of Context-sensitive Lexical Semantics
… This thesis sets out to answer the following two-fold research question: (1) how can we design a reliable evaluation framework that accurately reflects the challenges in contextual lexical semantics? And (2) how can we improve contextual word representations in a data-efficient manner? …
-
Discovering linguistic structures in speech : models and applications
… different acoustic conditions, domains, and languages, these models consistently demonstrate an ability to learn highly meaningful linguistic structures. In addition to learning sub-word and word-like units, we apply these models to the problem of one-shot learning tasks for spoken words, and …
-
Subword segmental neural language generation for Nguni languages
… primarily designed for a limited number of high-resource languages. These advances are not directly applicable to low-resource languages with distinctive linguistic characteristics. In this thesis we develop text generation models for the Nguni languages of South Africa -- isiXhosa, isiZulu, …
-
Crowdsourcing a text corpus for a low resource language
Low resourced languages, such as South Africa's isiXhosa, have a limited number of digitised texts, making it challenging to build language corpora and the information retrieval services, such as search and translation that depend on them. Researchers have been unable to assemble isiXhosa corpora …
-
Analyzing Networks with Hypergraphs: Detection, Classification, and Prediction
… tailored for sarcasm detection across multiple low-resource languages. Our model excels in interpreting the subtle and context-dependent nature of sarcasm in short texts by exploiting the power of hypergraph structures to capture complex, high-order relationships among words. Through the …
Page 1 of 2