Enhancing word and document embeddings for natural language processing tasks

Authors: Rafieian, Bardia

Contributors: University/Department: Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions

Thesis Advisors: Vázquez Alcocer, Pere Pau, Rodríguez Fonollosa, José Adrián

Source: TDX (Tesis Doctorals en Xarxa)

Subject Terms: Natural Language Processing, Word Embeddings, Document Embeddings, Neural Machine Translation, Biomedical Machine Translation, Recommender Systems, Content-Based Recommender Systems, Collaborative Filtering, Document Classification, Long Document Classification, Hierarchical Classification, Multi-label Classification, Patent Classification, Semantic Specialization, Large Language Models (LLMs), Transformers, LoRA, Quantization, Word2Vec, GloVe, Doc2Vec, SciBERT, Longformer, LLaMA-3, GEMMA-2B, BabelNet, Wasserstein GANs, Subword Optimization, Data Augmentation, Forward Translation, Domain Adaptation, Low-Resource NMT, Lexical Knowledge Integration, Computational Efficiency, Scalability, Spanish-English Machine Translation., Àrees temàtiques de la UPC::Enginyeria de la telecomunicació, Àrees temàtiques de la UPC::Enginyeria biomèdica, Àrees temàtiques de la UPC::Informàtica, 621.3 - Enginyeria elèctrica. Electrotècnia. Telecomunicacions, 004 - Informàtica

File Description: application/pdf

Access URL: http://hdl.handle.net/10803/696190
https://dx.doi.org/10.5821/dissertation-2117-449267

Feature Analysis of Tokenizers in Multi-Category Text Classification

Authors: Anandita, Valda Veisa Al Fatih, Richasdy, Donni, Gani, Prati Hutari

Source: 2026 5th International Conference on Electronics Representation and Algorithm (ICERA) Electronics Representation and Algorithm (ICERA), 2026 5th International Conference on. :217-222 Jul, 2026

Relation: 2026 5th International Conference on Electronics Representation and Algorithm (ICERA)

QuantumGPT: Adaptive Gated Head Pruning for Efficient Decoder-Only Language Models

Authors: Rastogi, Harsh, Pandey, Ankur, Kumar, Nischey, Ahmed, Zishan, Singh, Shilpi

Source: 2026 International Conference on Natural Language Processing and Computer Vision (ICNPCV) Natural Language Processing and Computer Vision (ICNPCV), 2026 International Conference on. :1-5 Jul, 2026

Relation: 2026 International Conference on Natural Language Processing and Computer Vision (ICNPCV)

The Context Tax of General-Purpose Tokenization

Authors: Sadak, Mustafa Semih

Source: 2026 34th Signal Processing and Communications Applications Conference (SIU) Signal Processing and Communications Applications Conference (SIU), 2026 34th. :1-4 Jul, 2026

Relation: 2026 34th Signal Processing and Communications Applications Conference (SIU)

Unsupervised Morphological Segmentation for Hybrid Tokenization in Uzbek NLP Pipelines

Authors: Safarov, Ruzmat, Davronov, Rifqat, Samariddin, Kushmuratov, Begimov, Abbos, Abduxakimova, Mo'Tabar, Khushvaqtov, Bayramali

Source: 2026 IEEE 27th International Conference of Young Professionals in Electron Devices and Materials (EDM) Young Professionals in Electron Devices and Materials (EDM), 2026 IEEE 27th International Conference of. :1-4 Jun, 2026

Relation: 2026 IEEE 27th International Conference of Young Professionals in Electron Devices and Materials (EDM)

An Efficient Algorithm for Streaming BPE Tokenization

Authors: Mamouras, Konstantinos, Li, Angela W., Yang, Yudi

Source: Proceedings of the ACM on Programming Languages. 10(PLDI):2085-2108

Availability: http://dl.acm.org/doi/10.1145/3808330

Modelling Subword Embeddings of Low-Resource Languages for the Digitalisation of Industry 4.0 Industrial Systems

Authors: Arabov, M. K., Gainullin, R. N., Khusaenov, A. I.

Source: 2026 International Russian Smart Industry Conference (SmartIndustryCon) Russian Smart Industry Conference (SmartIndustryCon), 2026 International. :74-79 Mar, 2026

Relation: 2026 International Russian Smart Industry Conference (SmartIndustryCon)

Subword Dictionary Learning and Segmentation for Expanding the Vocabulary of Automatic Speech Recognition in Tamil and Kannada

Authors: A, Madhavaraj, Pilar, Bharathi, Angarai Ganesan, Ramakrishnan

Source: ACM Transactions on Asian and Low-Resource Language Information Processing. 24(1):1-26

Availability: http://dl.acm.org/doi/10.1145/3705312

4 Understanding Natural Language Processing

Source: Mastering Prompt Engineering: A Guide to Crafting Effective Prompts. Jul 17, 2026

10 Build an Index

Source: Problem Solving with Python. Jun 23, 2026

3 Replace Text with Emoji

Source: Problem Solving with Python. Jun 23, 2026

A Comprehensive Review of Text Generation Techniques in Low-Resource Indian Languages

Authors: Shubro, S.D., Subbanna, N.

Source: IEEE Access Access, IEEE. 14:159802-159825 2026

Turkish Subword Segmentation: A Unified Intrinsic–Extrinsic Analysis

Authors: Kagan Gunes, U., YILDIZ, O.T., Karadeniz, I.

Source: IEEE Access Access, IEEE. 14:129475-129487 2026

Rethinking Input Construction for Webshell Detection: A Controlled Study of Tokenization, Chunking, and Feature Fusion

Authors: Kwon, J.

Source: IEEE Access Access, IEEE. 14:125340-125359 2026

Efficient Transformer Models via Language-Aware Frequency-Based Vocabulary Pruning

Authors: Fuadi, M., Wibawa, A.D., Sumpeno, S.

Source: IEEE Access Access, IEEE. 14:50993-51006 2026

Some New Examples of Infinite-Type Interval Translation Maps

Authors: Chernyi, Valentin^{Aff1, ID1068820261221_cor1}

Source: Functional Analysis and Its Applications. 60(3):294-308

Geometric Realizations of ν\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\nu $$\end{document}-associahedra via Brick Polyhedra

Authors: Ceballos, Cesar^{Aff1, IDs0045402500766x_cor1}, Müller, Matthias^{Aff1, IDs0045402500766x_cor2}

Source: Discrete & Computational Geometry. 76(2):775-803

Analysis of the Efficiency of Subword Tokenizers in a Low-Resource Linguistic Environment: Implementation Experience for the Tajik Language

Authors: Arabov, M. K.^{Aff1, IDS0005105526700391_cor1}, Khaybullina, S. S.^{Aff1, IDS0005105526700391_cor2}

Source: Automatic Documentation and Mathematical Linguistics. 60(Suppl 2):S225-S230

Tom: A Domain-Aware Tokenization Metric for Medical NLP

Authors: Yu, Min-Yung, Yoo, Jae-Chern

Source: 2025 17th International Conference on Bioinformatics and Biomedical Technology (ICBBT) Bioinformatics and Biomedical Technology (ICBBT), 2025 17th International Conference on. :343-348 May, 2025

Relation: 2025 17th International Conference on Bioinformatics and Biomedical Technology (ICBBT)

Codeword Decomposition and Recoding Based Lossless Model Compression Algorithm and Its VLSI Decompressor Design

Authors: Ho, Lyu-Ming, Liang, Chih-Yao, Huang, Juinn-Dar

Source: 2025 IEEE 7th International Conference on Artificial Intelligence Circuits and Systems (AICAS) Artificial Intelligence Circuits and Systems (AICAS), 2025 IEEE 7th International Conference on. :1-5 Apr, 2025

Relation: 2025 IEEE 7th International Conference on Artificial Intelligence Circuits and Systems (AICAS)