Tootfinder

Tokenization Strategies for Low-Resource Agglutinative Languages in Word2Vec: Case Study on Turkish and Finnish
Jinfan Frank Hu
https://arxiv.org/abs/2509.14238 https://

Tokenization Strategies for Low-Resource Agglutinative Languages in Word2Vec: Case Study on Turkish and Finnish
Tokenization plays a critical role in processing agglutinative languages, where a single word can encode multiple morphemes carrying syntactic and semantic information. This study evaluates the impact of various tokenization strategies - word-level, character-level, n-gram, and Byte Pair Encoding (BPE) - on the quality of static word embeddings generated by Word2Vec for Turkish and Finnish. Using a 10,000-article Wikipedia corpus, we trained models under low-resource conditions and evaluated th…

Variable Rate Image Compression via N-Gram Context based Swin-transformer
Priyanka Mudgal, Feng Liu
https://arxiv.org/abs/2510.00058 https://arxiv.org/pdf/…

Variable Rate Image Compression via N-Gram Context based Swin-transformer
This paper presents an N-gram context-based Swin Transformer for learned image compression. Our method achieves variable-rate compression with a single model. By incorporating N-gram context into the Swin Transformer, we overcome its limitation of neglecting larger regions during high-resolution image reconstruction due to its restricted receptive field. This enhancement expands the regions considered for pixel restoration, thereby improving the quality of high-resolution reconstructions. Our m…

Regular Expression Indexing for Log Analysis. Extended Version
Ling Zhang, Shaleen Deep, Jignesh M. Patel, Karthikeyan Sankaralingam
https://arxiv.org/abs/2510.10348 https://

Regular Expression Indexing for Log Analysis. Extended Version
In this paper, we present the design and architecture of REI, a novel system for indexing log data for regular expression queries. Our main contribution is an $n$-gram-based indexing strategy and an efficient storage mechanism that results in a speedup of up to 14x compared to state-of-the-art regex processing engines that do not use indexing, using only 2.1% of extra space. We perform a detailed study that analyzes the space usage of the index and the improvement in workload execution time, un…

Sums of projections with random coefficients
Leonid Pastur, Alexander Pushnitski
https://arxiv.org/abs/2509.21539 https://arxiv.org/pdf/2509.21539

Sums of projections with random coefficients
We study infinite sums \[ {\mathcal P}_{\varkappa}=\sum_{n=-\infty}^\infty \varkappa_n \langle\cdot, ψ_n\rangleψ_n \] of rank-one projections in a Hilbert space, where $\{ψ_n\}_{n\in\mathbb Z}$ are norm-one vectors, not necessarily orthogonal, and $\{\varkappa_n\}_{n\in\mathbb Z}$ are independent identically distributed positive random variables. Assuming that the Gram matrix $\{\langleψ_n,ψ_m\rangle\}_{n,m\in\mathbb Z}$ defines a bounded operator on $\ell^2(\mathbb Z)$ and that its entrie…

Resolution scaling governs DINOv3 transfer performance in chest radiograph classification
Soroosh Tayebi Arasteh, Mina Shaigan, Christiane Kuhl, Jakob Nikolas Kather, Sven Nebelung, Daniel Truhn
https://arxiv.org/abs/2510.07191

Resolution scaling governs DINOv3 transfer performance in chest radiograph classification
Self-supervised learning (SSL) has advanced visual representation learning, but its value in chest radiography, a high-volume imaging modality with fine-grained findings, remains unclear. Meta's DINOv3 extends earlier SSL models through Gram-anchored self-distillation. Whether these design choices improve transfer learning for chest radiography has not been systematically tested. We benchmarked DINOv3 against DINOv2 and ImageNet initialization across seven datasets (n>814,000). Two representati…

Death of the Novel(ty): Beyond n-Gram Novelty as a Metric for Textual Creativity
Arkadiy Saakyan, Najoung Kim, Smaranda Muresan, Tuhin Chakrabarty
https://arxiv.org/abs/2509.22641

Death of the Novel(ty): Beyond n-Gram Novelty as a Metric for Textual Creativity
N-gram novelty is widely used to evaluate language models' ability to generate text outside of their training data. More recently, it has also been adopted as a metric for measuring textual creativity. However, theoretical work on creativity suggests that this approach may be inadequate, as it does not account for creativity's dual nature: novelty (how original the text is) and appropriateness (how sensical and pragmatic it is). We investigate the relationship between this notion of creativity …

A Formal Framework for Fluency-based Multi-Reference Evaluation in Grammatical Error Correction
Eitan Klinger, Zihao Huang, Tran Minh Nguyen, Emma Jayeon Park, Yige Chen, Yang Gu, Qingyu Gao, Siliang Liu, Mengyang Qiu, Jungyeul Park
https://arxiv.org/abs/2510.06749

A Formal Framework for Fluency-based Multi-Reference Evaluation in Grammatical Error Correction
Evaluating grammatical error correction requires metrics that reflect the diversity of valid human corrections rather than privileging a single reference. Existing frameworks, largely edit-based and English-centric, rely on rigid alignments between system and reference edits, limiting their applicability in multilingual and generative settings. This paper introduces a formal framework for \textit{fluency-based multi-reference evaluation}, framing $n$-gram similarity as an aggregation problem ov…

RadEval: A framework for radiology text evaluation
Justin Xu, Xi Zhang, Javid Abderezaei, Julie Bauml, Roger Boodoo, Fatemeh Haghighi, Ali Ganjizadeh, Eric Brattain, Dave Van Veen, Zaiqiao Meng, David Eyre, Jean-Benoit Delbrouck
https://arxiv.org/abs/2509.18030

RadEval: A framework for radiology text evaluation
We introduce RadEval, a unified, open-source framework for evaluating radiology texts. RadEval consolidates a diverse range of metrics, from classic n-gram overlap (BLEU, ROUGE) and contextual measures (BERTScore) to clinical concept-based scores (F1CheXbert, F1RadGraph, RaTEScore, SRR-BERT, TemporalEntityF1) and advanced LLM-based evaluators (GREEN). We refine and standardize implementations, extend GREEN to support multiple imaging modalities with a more lightweight model, and pretrain a doma…

Dorabella Cipher as Musical Inspiration
Bradley Hauer, Colin Choi, Abram Hindle, Scott Smallwood, Grzegorz Kondrak
https://arxiv.org/abs/2509.17950 https://

Dorabella Cipher as Musical Inspiration
The Dorabella cipher is an encrypted note written by English composer Edward Elgar, which has defied decipherment attempts for more than a century. While most proposed solutions are English texts, we investigate the hypothesis that Dorabella represents enciphered music. We weigh the evidence for and against the hypothesis, devise a simplified music notation, and attempt to reconstruct a melody from the cipher. Our tools are n-gram models of music which we validate on existing music corpora enci…