相关论文: Tokenization vs. Augmentation: A Systematic Study …

Subword tokenization is the de facto standard for tokenization in neural language models and machine translation systems. Three advantages are frequently cited in favor of subwords: shorter encoding of frequent tokens, compositionality of…

Most pretrained language models rely on subword tokenization, which processes text as a sequence of subword tokens. However, different granularities of text, such as characters, subwords, and words, can contain different kinds of…

Tokenization is the first step in every language model (LM), yet it never takes the sounds of words into account. We investigate how tokenization influences text-only LMs' ability to represent phonological knowledge. Through a series of…

On-line handwritten character segmentation is often associated with handwriting recognition and even though recognition models include mechanisms to locate relevant positions during the recognition process, it is typically insufficient to…

Large annotated datasets have been a key component in the success of deep learning. However, annotating medical images is challenging as it requires expertise and a large budget. In particular, annotating different types of cells in…

Language-independent tokenisation (LIT) methods that do not require labelled language resources or lexicons have recently gained popularity because of their applicability in resource-poor languages. Moreover, they compactly represent a…

We present a framework for learning an efficient holistic representation for handwritten word images. The proposed method uses a deep convolutional neural network with traditional classification loss. The major strengths of our work lie in:…

Personalizing dysarthric ASR is hindered by demanding enrollment collection and per-user training. We propose a hybrid meta-training method for a single model, enabling zero-shot and few-shot on-the-fly personalization via in-context…

Text data augmentation is a widely used strategy for mitigating data sparsity in natural language processing (NLP), particularly in low-resource settings where limited samples hinder effective semantic modeling. While augmentation can…

Meta-learning for algorithm selection relies on a meta-dataset in which each row corresponds to a supervised learning dataset described by meta-features and labelled with a target value that is associated with algorithm choice (typically,…

In this paper we deal with the offline handwriting text recognition (HTR) problem with reduced training datasets. Recent HTR solutions based on artificial neural networks exhibit remarkable solutions in referenced databases. These deep…

Text watermarking plays a crucial role in ensuring the traceability and accountability of large language model (LLM) outputs and mitigating misuse. While promising, most existing methods assume perfect pseudorandomness. In practice,…

The Word Error Rate (WER) is the common measure of accuracy for Automatic Speech Recognition (ASR). Transcripts are usually pre-processed by substituting specific characters to account for non-semantic differences. As a result of this…

Transformers achieve unrivalled performance in modelling language, but remain inefficient in terms of memory and time complexity. A possible remedy is to reduce the sequence length in the intermediate layers by pooling fixed-length segments…

Online handwriting recognition has been studied for a long time with only few practicable results when writing on normal paper. Previous approaches using sensor-based devices encountered problems that limited the usage of the developed…

The size of the vocabulary is a central design choice in large pretrained language models, with respect to both performance and memory requirements. Typically, subword tokenization algorithms such as byte pair encoding and WordPiece are…

Homophone characters are common in tonal syllable-based languages, such as Mandarin and Cantonese. The data-intensive end-to-end Automatic Speech Recognition (ASR) systems are more likely to mis-recognize homophone characters and rare words…

All languages are equal; when it comes to tokenization, some are more equal than others. Tokens are the hidden currency that dictate the cost and latency of access to contemporary LLMs. However, many languages written in non-Latin scripts…

Reinforcement learning with verifiable rewards (RLVR) has significantly improved reasoning in large language models (LLMs), yet the token-level mechanisms underlying these improvements remain unclear. We present a systematic empirical study…

Data augmentation is commonly used to help build a robust speaker verification system, especially in limited-resource case. However, conventional data augmentation methods usually focus on the diversity of acoustic environment, leaving the…