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 21 for “"beam search"”.
-
PropRAG: Guiding retrieval with beam search over proposition paths
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms
-
Structured Learning with Inexact Search: Advances in Shift-Reduce CCG Parsing
… learning, structured learning, and inexact search. This dissertation considers approaches that tightly integrate these three elements and explores three novel models for shift-reduce CCG parsing. First, I develop a dependency model, in which the selection of shift-reduce action sequences …
-
Efficient methods for mapping neural machine translator on FPGAs
… recurrent units (GRU), attention mechanisms, and beam-search algorithms, for improved translation quality. However, with the increasing problem size, the real-life NMT models have become much more complicated and difficult to implement on hardware for acceleration opportunities. In this thesis, we …
-
Similarity-Augmented Prediction Methods for Neural Machine Translation
… the effectiveness of probability maximizing search for prediction, e.g. beam search, and probability-based uncertainty quantification (UQ), e.g. Shannon entropy. In this thesis, we study a class of methods which measure semantic similarities between elements in the LM output distribution, …
-
Optimizing Priority-Based Search for Lifelong Multi-Agent Path Finding
… Traditional solvers such as Priority-Based Search (PBS) use fixed branching heuristics, which can be inefficient in high-congestion scenarios. This work explores how learning-based methods can improve PBS decision-making. We develop supervised learning (SL) policies trained from high-quality …
-
Deep Generative Models for Trajectory Prediction and Mobility Network Forecasting
… sequences and employs spatially constrained beam search to predict each individuals’s next k locations with high precision. Building on these forecasts, we present MobiNetForecast, which constructs and predicts the future topology of the mobility network by detecting when independently …
-
EFFORTS TOWARD TRUSTWORTHY MACHINE LEARNING: MITIGATING OVERCONFIDENCE, HALLUCINATION, AND MODALITY BIAS
… decoding, which evaluates candidates during beam search to produce more faithful and visually grounded outputs. Finally, we study modality bias, revealing “blind faith in text” across LVLMs and showing that supervised fine-tuning with text augmentation reduces this imbalance. Together, these …
-
Generování stylizovaného lidského jazyka v dialogových systémech
… dekódování jazykových modelů byly použity Beam search a Nucleus sampling. Navrhované experimenty jsou založeny na váženém dekódování. Zejména pravděpodobnostní funkce vypočítaná pomocí jazykového modelu, který generuje odpověď, je modifikována dvěma přístupy. První přístup používá ručně …
-
Spontaneous speech recognition using HMMs
… bigram statistical language model, and (4) a beam search decoder based on the Viterbi algorithm. The contextdependent acoustic models resulted in 67.9% phoneme recognition accuracy on the standard TIMIT speech database. Spontaneous speech was collected using a "Wizard of Oz" simulation of a …
-
Data Augmentation with Seq2Seq Models
… we sample the neural network using diverse beam search. We evaluate the results on the standard VQA validation set. Our approach results in a significantly expanded training dataset and vocabulary size, but has slightly worse performance when tested on the validation split. Although not as …
-
Greedy Inference Algorithms for Structured and Neural Models
… outputs in high-dimensional space, which makes searching for the global optimal solution extremely expensive. Thus, greedy algorithms, making trade-offs between precision and efficiency, are widely used. Unfortunately, they in general lack theoretical guarantees. In this thesis, we prove that …
-
Application-driven Intersections between Information Theory and Machine Learning
… in machine translation for selecting the beam size in beam search.
-
Helping Developers Migrate their Code across Programming Languages
… For code-reuse, two new cross-language code search techniques are proposed that enable developers to search for code in one language using code from another. These techniques address the limitations of existing methods in the context of code migration. The first technique leverages a Siamese …
-
Terrain-relative navigation for autonomous underwater vehicles
… a coarse-to-fine algorithm with a modified beam search is used to intelligently search for good matches while reducing the computational requirements. A validation gate is defined around the position estimate using the navigation uncertainty, which is explicitly represented through a …
-
Lagrangian relaxation for natural language decoding
… complex models come at the cost of expanding the search-space of the underlying decoding problem. In this dissertation, we focus on the question of how to handle this challenge. In particular, we study the question of decoding in large-scale, statistical natural language systems. We aim to develop …
-
Exact Sampling and Optimisation in Statistical Machine Translation
… either to perform optimisation { the task of searching for the optimum translation { or sampling { the task of nding a subset of translations that is statistically representative of the goal distribution. Beam-search is an example of an approximate optimisation technique, where maximisation is …
-
The Use of Language Models in End-to-End Spoken Language Processing
… using a pre-trained vocoder. An incremental beam search is designed to expand the search space of speech token prediction without increasing latency. Experiments on the CVSS speech data showed that SimulS2S-LLM offers a better translation quality-latency trade-off than existing methods that …
-
End-to-end Contextual Speech Recognition and Understanding
… such that knowledge explored during ASR beam search decoding can be transferred to the generation of slot values. The KA2G framework achieves further performance improvements compared to the SPB mechanism, especially on few-shot entities by exposing only a handful of examples to the model …
-
Improving manufacturing operations using deep learning: Multi-faceted research in monitoring, diagnosis, and optimization
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms
-
The permutation flowshop scheduling problem: analysis, solution procedures and problem extensions
… one of the most studied problems in Operations Research. There are several reasons for this fact: On the one hand, the flow shop layout is the common configuration in many real manufacturing scenarios, as it presents several advantages over more general job shop configuration, and, in addition, …
Page 1 of 2