English
Related papers

Related papers: H-Net++: Hierarchical Dynamic Chunking for Tokeniz…

200 papers

Dynamic networks have shown their promising capability in reducing theoretical computation complexity by adapting their architectures to the input during inference. However, their practical runtime usually lags behind the theoretical…

Computer Vision and Pattern Recognition · Computer Science 2021-09-22 Changlin Li , Guangrun Wang , Bing Wang , Xiaodan Liang , Zhihui Li , Xiaojun Chang

Signals from different modalities each have their own combination algebra which affects their sampling processing. RGB is mostly linear; depth is a geometric signal following the operations of mathematical morphology. If a network obtaining…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Rick Groenendijk , Leo Dorst , Theo Gevers

Pre-trained language models (PLMs) have shown remarkable successes in acquiring a wide range of linguistic knowledge, relying solely on self-supervised training on text streams. Nevertheless, the effectiveness of this language-agnostic…

Computation and Language · Computer Science 2023-11-02 Eylon Gueta , Omer Goldman , Reut Tsarfaty

Translation into morphologically-rich languages challenges neural machine translation (NMT) models with extremely sparse vocabularies where atomic treatment of surface forms is unrealistic. This problem is typically addressed by either…

Computation and Language · Computer Science 2020-02-28 Duygu Ataman , Wilker Aziz , Alexandra Birch

The study explores the integration of transfer learning (TL) with mobile-enabled convolutional neural networks (MbNets) to enhance Arabic Handwritten Character Recognition (AHCR). Addressing challenges like extensive computational…

Computer Vision and Pattern Recognition · Computer Science 2025-09-08 Mohsine El Khayati , Ayyad Maafiri , Yassine Himeur , Hamzah Ali Alkhazaleh , Shadi Atalla , Wathiq Mansoor

Automated knowledge graph (KG) construction is essential for navigating the rapidly expanding body of scientific literature. However, existing approaches struggle to recognize long multi-word entities, often fail to generalize across…

Computation and Language · Computer Science 2026-03-25 Devvrat Joshi , Islem Rekik

Current state-of-the-art models for natural language understanding require a preprocessing step to convert raw text into discrete tokens. This process known as tokenization relies on a pre-built vocabulary of words or sub-word morphemes.…

Computation and Language · Computer Science 2023-05-31 Li Sun , Florian Luisier , Kayhan Batmanghelich , Dinei Florencio , Cha Zhang

Large pre-trained multilingual models like mBERT, XLM-R achieve state of the art results on language understanding tasks. However, they are not well suited for latency critical applications on both servers and edge devices. It's important…

Computation and Language · Computer Science 2021-01-25 Prabhu Kaliamoorthi , Aditya Siddhant , Edward Li , Melvin Johnson

The prevalence of Transformer-based pre-trained language models (PLMs) has led to their wide adoption for various natural language processing tasks. However, their excessive overhead leads to large latency and computational costs. The…

Computation and Language · Computer Science 2023-05-23 Wenxi Tan

Transformer-based models, specifically BERT, have propelled research in various NLP tasks. However, these models are limited to a maximum token limit of 512 tokens. Consequently, this makes it non-trivial to apply it in a practical setting…

Computation and Language · Computer Science 2023-11-01 Aman Jaiswal , Evangelos Milios

This paper presents the first comprehensive comparative analysis of modern machine learning architectures for transliteration between Tajik (Cyrillic script) and Persian (Arabic script). A key contribution is the creation and validation of…

Computation and Language · Computer Science 2026-05-05 Mullosharaf K. Arabov

Very deep CNNs with small 3x3 kernels have recently been shown to achieve very strong performance as acoustic models in hybrid NN-HMM speech recognition systems. In this paper we investigate how to efficiently scale these models to larger…

Computation and Language · Computer Science 2016-06-28 Tom Sercu , Vaibhava Goel

We propose an end-to-end joint optimization framework of a multi-channel neural speech extraction and deep acoustic model without mel-filterbank (FBANK) extraction for overlapped speech recognition. First, based on a multi-channel…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-31 Bo Wu , Meng Yu , Lianwu Chen , Chao Weng , Dan Su , Dong Yu

Tokenization is a pivotal design choice for neural language modeling in morphologically rich languages (MRLs) such as Turkish, where productive agglutination challenges both vocabulary efficiency and morphological fidelity. Prior studies…

Computation and Language · Computer Science 2026-02-09 Duygu Altinok

Common subword tokenization algorithms like BPE and UnigramLM assume that text can be split into meaningful units by concatenative measures alone. This is not true for languages such as Hebrew and Arabic, where morphology is encoded in…

Computation and Language · Computer Science 2025-06-04 Bar Gazit , Shaltiel Shmidman , Avi Shmidman , Yuval Pinter

Remote sensing semantic segmentation requires models that can jointly capture fine spatial details and high-level semantic context across complex scenes. While classical encoder-decoder architectures such as U-Net remain strong baselines,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-01 Md Aminur Hossain , Ayush V. Patel , Siddhant Gole , Sanjay K. Singh , Biplab Banerjee

Discrete speech tokenization is a fundamental component in speech codecs. However, in large-scale speech-to-speech systems, the complexity of parallel streams from multiple quantizers and the computational cost of high-time-dimensional…

Sound · Computer Science 2025-07-28 Rongkun Xue , Yazhe Niu , Shuai Hu , Zixin Yin , Yongqiang Yao , Jing Yang

Few-shot semantic segmentation aims at learning to segment a target object from a query image using only a few annotated support images of the target class. This challenging task requires to understand diverse levels of visual cues and…

Computer Vision and Pattern Recognition · Computer Science 2021-10-18 Juhong Min , Dahyun Kang , Minsu Cho

The current pretraining paradigm for large language models relies on massive compute and internet-scale raw text, creating a significant barrier to foundational research. In contrast, biological systems demonstrate highly sample-efficient…

Computation and Language · Computer Science 2026-05-21 Guan Wang , Changling Liu , Chenyu Wang , Cai Zhou , Yuhao Sun , Yifei Wu , Shuai Zhen , Luca Scimeca , Yasin Abbasi Yadkori

While model architecture and training objectives are well-studied, tokenization, particularly in multilingual contexts, remains a relatively neglected aspect of Large Language Model (LLM) development. Existing tokenizers often exhibit high…

‹ Prev 1 4 5 6 7 8 10 Next ›