Related papers: VerChol -- Grammar-First Tokenization for Agglutin…

This study investigates the impact of morphological typology on tokenization and language modeling performance. We focus on languages with synthetic and analytical morphological structures and examine their productivity when tokenized using…

Spoken language models (SLMs) typically discretize speech into high-frame-rate tokens extracted from SSL speech models. As the most successful LMs are based on the Transformer architecture, processing these long token streams with…

Quite often, words from one language are adopted within a different language without translation; these words appear in transliterated form in text written in the latter language. This phenomenon is particularly widespread within Indian…

Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of teacher confidence. This indiscriminate supervision amplifies…

The cold-start issue is the challenge when we talk about recommender systems, especially in the case when we do not have the past interaction data of new users or new items. Content-based features or hybrid solutions are common as…

NMT systems have problems with large vocabulary sizes. Byte-pair encoding (BPE) is a popular approach to solving this problem, but while BPE allows the system to generate any target-side word, it does not enable effective generalization…

By processing electronic health records (EHRs) as natural language sequences, large language models (LLMs) have shown potential in clinical prediction tasks such as mortality prediction and phenotyping. However, longitudinal or highly…

Large language models (LLMs) have revolutionized natural language processing, yet they remain constrained by fixed, non-differentiable tokenizers like Byte Pair Encoding (BPE), which hinder end-to-end optimization and adaptability to noisy…

In this paper, we consider block languages, namely sets of words having the same length, and we propose a new representation for these languages. In particular, given an alphabet of size $k$ and a length $\ell$, a block language can be…

Tokenization is fundamental to how language models represent and process text, yet the behavior of widely used BPE tokenizers has received far less study than model architectures and training. In this paper, we investigate intermediate…

A good language model starts with a good tokenizer. Tokenization is especially important for speech modeling, which must handle continuous signals that mix linguistic and non-linguistic information. A speech tokenizer should extract…

Large Language Models (LLMs) have become a cornerstone in Natural Language Processing (NLP), achieving impressive performance in text generation. Their token-level representations capture rich, human-aligned semantics. However, pooling…

Byte Pair Encoding (BPE) is a widely used tokenization algorithm, whose tokens cannot extend across pre-tokenization boundaries, functionally limiting it to representing at most full words. The BoundlessBPE and SuperBPE algorithms extend…

While most frontier models still use deterministic frequency-based tokenization algorithms such as byte-pair encoding (BPE), there has been significant recent work to design learned neural tokenizers. However, these schemes generally add to…

The first step in any NLP pipeline is to split the text into individual tokens. The most obvious and straightforward approach is to use words as tokens. However, given a large text corpus, representing all the words is not efficient in…

This paper proposes a unimodal aggregation (UMA) based nonautoregressive model for both English and Mandarin speech recognition. The original UMA explicitly segments and aggregates acoustic frames (with unimodal weights that first…

Autoregressive language models generate text one token at a time, yet natural language is inherently structured in multi-token units, including phrases, n-grams, and collocations that carry meaning jointly. This one-token bottleneck limits…

The advancements in the Large Language Model (LLM) have helped in solving several problems related to language processing. Most of the researches have focused on the English language only, because of its popularity and abundance on the…

The purpose of speech tokenization is to transform a speech signal into a sequence of discrete representations, serving as the foundation for speech language models (SLMs). While speech tokenization has many options, their effect on the…

This paper investigates the effect of tokenizers on the downstream performance of pretrained language models (PLMs) in scriptio continua languages where no explicit spaces exist between words, using Japanese as a case study. The tokenizer…