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 186 for “"sequence-to-sequence"”.
-
Sequence-to-Sequence Automatic Sentence Simplification: Development & Evaluation
… the transformation of complex sentences into simpler versions, addressing syntactic and lexical aspects through operations such as rephrasing, addition, deletion, splitting, or substitution. The Sequence-to-Sequence (Seq2Seq) model has demonstrated significant efficacy across various …
-
Tackling sequence to sequence mapping problems with neural networks
… Language Processing (NLP), it is important to detect the relationship between two sequences or to generate a sequence of tokens given another observed sequence. We call the type of problems on modelling sequence pairs as sequence to sequence (seq2seq) mapping problems. A lot of research has …
-
Interactivity, Adaptation and Multimodality in Neural Sequence-to-sequence Learning
… entre los cuales destacan la traducción automática o la descripción automática de objetos multimedia. La aplicación de redes neuronales profundas ha revolucionado esta disciplina, y se han logrado avances notables. Pero los sistemas automáticos todavía producen predicciones que distan mucho …
-
Applying sequence-to-sequence RNN models to IR-based bug localization
… and money could be saved if this process was automated. Bug localization based on information retrieval (IR) is a static approach to automation that represents source code files as documents in a database and bug reports as queries. The bug localization approach described in this report is …
-
Towards Effectively Testing Sequence-to-Sequence models from White-Box Perspectives
… progress, NLP systems, including those based on sequence-to-sequence models, confront various challenges. To tackle these, metamorphic testing methods have been employed across different NLP tasks. These methods entail task-specific adjustments at the token or sentence level. For example, in …
-
Question Generation Using Sequence-to-Sequence Model with Semantic Role Labels
Automatic generation of questions from text has gained increasing attention due to its useful applications. We propose a novel question generation method that combines the benefits of rule-based and neural sequence-to-sequence (Seq2Seq) models. The proposed method can automatically generate …
-
Query-focused abstractive summarization using sequence-to-sequence and transformer models
… (QFS) summarizes a long document with respect to a given input query. Creating a query-focused abstractive summary by using a neural network model is a difficult task which is yet to be fully solved. In our thesis, we propose two neural network models for the query-focused abstractive …
-
Attention-based neural sequence-to-sequence methods for information extraction and text summarization
… of NLP tasks. Such models are often trained end-to-end and are more efficient and cost-effective than traditional task-specific feature engineering. In this dissertation, we focus on several NLP tasks using a specific deep learning technique -- sequence-to-sequence (seq2seq). We first explore the …
-
XceptionLSTM: Advanced Sequence-to-Sequence Neural Networks for Short-Term Weather Forecasting Applications
Η παγκόσμια τάση των τελευταίων δύο δεκαετιών για ανεξαρτητοποίηση από κάυσιμες πηγές ενέργειας έχει οδηγήσει τη βιομηχανία ενέργειας προς την αξιοποίηση ανανεώσημων πηγών ενέργειας. Η μετάβαση σε πιο πράσινη ενέργεια αποτελεί έμπνευση ιδέων και πρακτικών που αποσκοπούν στον έλεγχο της παραγωγής …
-
Speech to Text to Semantics: A Sequence-to-Sequence System for Spoken Language Understanding
Spoken language understanding entails both the automatic transcription of a speech utterance and the identification of one or more semantic concepts being conveyed by the utterance. Traditionally these systems are domain specific and target industries like travel, entertainment, and home …
-
LSTM sequence-to-sequence based System Identification and feedforward-feedback control of piezoelectric actuators
Piezo-electric actuators (PEA) have wide applications in nano/micro-positioning systems, such as Atomic Force Microscopy (AFM), micro-forming/machining, adaptive optics, and more. The popularity of PEA applications come from its advantages, including high resolution, high stiffness, and fast …
-
Comparison of Sequence-to-Sequence and Retrieval Approaches on the Code Summarization and Code Generation Tasks
… generation and code summarization tasks (English-to-code and code-to-English). We compare the performance of neural seq2seq BiLSTM [Yin et al. 2018] and attentional-GRU architectures [LeClair et al. 2019], along with that of a semantic code search model reproduced from [Sachdev et al. 2018]. We …
-
Theoretical Expressivity of Self-Attention as a Model of Binary Sequence-To-Sequence Functions and Other Explorations
… (LLMs). The basic role of self-attention is to capture pairwise interactions between tokens in a sequence. This allows token embeddings to be endowed with context-dependent information before further processing. Despite its widespread use, our theoretical understanding of self-attention is …
-
Data Augmentation with Seq2Seq Models
… corpus for the visual question answering system to make it more robust to paraphrases. This corpus is generated by concatenating two sequence to sequence models. In order to generate diverse paraphrases, we sample the neural network using diverse beam search. We evaluate the results on the …
-
Neural Network vs. Rule-Based G2P: A Hybrid Approach to Stress Prediction and Related Vowel Reduction in Bulgarian
An effective grapheme-to-phoneme (G2P) conversion system is a critical element of speech synthesis. Rule-based systems were an early method for G2P conversion. In recent years, machine learning tools have been shown to outperform rule-based approaches in G2P tasks. We investigate neural network …
-
Neural Network Approaches to Implicit Discourse Relation Recognition
In order to understand a coherent text, humans infer semantic or logical relations between textual units. For example, in ``I am hungry. I did not have lunch today.'' the reader infers a ``causality'' relation even if it is not explicitly stated via a term such as ``because''. The linguistic device …
-
Rozpoznávání ručně psaného textu pomocí hlubokých neuronových sítí
Táto práca sa zaoberá problematikou rozpoznávania ručne písaného textu pomocou hlbokých neurónových sietí. Je zameraná na použitie metódy sequence to sequence pomocou enkóder-dekóder modelu. Jej súčasťou je aj návrh enkóder-dekóder modelu pre rozpoznávanie ručne písaného písma používajúceho …
-
Towards End-to-end Non-autoregressive speech applications
… speech research community, a very challenging topic researchers are interested in is the sequence-to-sequence labeling problem. Speech is a complicated signal, and many tasks aim to assign a sequence of various labels to the signal. Before, the traditional hybrid approach models this problem as …
-
Code representation learning with Prüfer sequences
… and efficient code representation is critical to the success of sequence-to-sequence deep neural network models for a variety of tasks in code understanding, such as code summarization and documentations, improving productivity, and reducing software development costs. Unlike the natural …
Page 1 of 10