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 10 of 10 for “"Seq2Seq"”.
-
Data Augmentation with Seq2Seq Models
Paraphrase sparsity is an issue that complicates the training process of question answering systems: syntactically diverse but semantically equivalent sentences can have significant disparities in predicted output probabilities. We propose a method for generating an augmented paraphrase corpus for …
-
On Natural Motion Processing using Inertial Motion Capture and Deep Learning
… from sparse sensors using Transformers and Seq2Seq models. We found that Transformers perform better than Seq2Seq models in producing upper-body and full-body motion, but that each model can accurately infer human motion for a variety of postures like sitting, standing, kneeling, and bending …
-
Adversarial training objectives for generative attacks on text classifiers
… start with a pre-trained sequence-to-sequence (seq2seq) transformer model and fine-tune it to generate adversarial content, offer benefits like efficiency and parallel processing capabilities. Despite these advantages, generative methods remain under-explored and lack established training …
-
Autonomous vehicles that understand road agents: Detection, tracking, and behavior prediction
… of road agents. We introduce the Fusion Seq2Seq model and compare it with two other baseline models. Experiments on a driver behavior dataset shows that our model can reasonably predict ego-vehicle actions.
-
Application-driven Intersections between Information Theory and Machine Learning
… problem. We study machine translation using the seq2seq model and we provide insights into quantifying the uncertainty within. Our results shed light on the design of inference in machine translation for selecting the beam size in beam search.
-
A deeper look into multi-task learning ability of unified text-to-text transformer
… SP tasks. These models convert SP tasks into a seq2seq problem, where a transformer is used to generate sequences with special tokens representing the extracted spans, labels, and relationships. Compared to many popular Natural Language Understanding models that are designed specifically for the …
-
Human Pose Estimation and Algorithms for Alignment and Registration Problems: Applications in Robotics, Computer Vision, and Stroke Rehabilitation
… and evaluate a family of deep sequence models—Seq2Seq, Seq2Seq with BiRNN and attention, a Transformer encoder, and a full Transformer—to infer multi-joint upper-body orientations (15 segments) from the three-IMU streams. Transformers, particularly the full encoder–decoder variant, achieve …
-
A system framework for non-intrusive monitoring of HMI states for detecting human-in-the-loop error precursors
… (RNN and CNN) for HMI time-series modeling; and Seq2Seq deep learning natural language processing (NLP) models for HMI discrete event system model. As an example, relative root-mean-square-error in forecast accuracy is RMSE ~ [30%; 80%; 100%] for N - ahead > 10 time-step forecast window. This …
-
Deep Learning Models for Traffic Prediction in Urban Transport Networks.
… Neural Network and Transformer, named GCNT-Seq2Seq, for long-term traffic speed prediction in large-scale road net- works. This model is able to analyse and extract local- and global-spatial and long-term temporal features for the final prediction, which benefits the optimisation of traffic …
-
Generování stylizovaného lidského jazyka v dialogových systémech
Tato práce se zabývá přístupy generování přirozeného jazyka v různých stylech. Kromě toho také zkoumá schopnost modelů řídit sílu projevu stylu v generované sekvenci. Model pro generování přirozeného jazyka byl implementován s několika aspekty projevů stylu, konkrétně poezie, humor, sentiment a …