Related papers: SampoNLP: A Self-Referential Toolkit for Morpholog…

This research addresses the problem of acoustic modeling of low-resource languages for which transcribed training data is absent. The goal is to learn robust frame-level feature representations that can be used to identify and distinguish…

Recent advances in word embeddings and language models use large-scale, unlabelled data and self-supervised learning to boost NLP performance. Multilingual models, often trained on web-sourced data like Wikipedia, face challenges: few…

The reliability of multilingual Large Language Model (LLM) evaluation is currently compromised by the inconsistent quality of translated benchmarks. Existing resources often suffer from semantic drift and context loss, which can lead to…

Prompt optimization is a practical and widely applicable alternative to fine tuning for improving large language model performance. Yet many existing methods evaluate candidate prompts by sampling full outputs, often coupled with self…

This memoir explores two fundamental aspects of Natural Language Processing (NLP): the creation of linguistic resources and the evaluation of NLP system performance. Over the past decade, my work has focused on developing a morpheme-based…

We present a language independent, unsupervised method for building word embeddings using morphological expansion of text. Our model handles the problem of data sparsity and yields improved word embeddings by relying on training word…

In hybrid automatic speech recognition (ASR) systems, the vocabulary size is unambiguous, typically determined by the number of phones, bi-phones, or tri-phones present in the language. In contrast, end-to-end ASR systems derive their…

This paper presents a comprehensive examination of the impact of tokenization strategies and vocabulary sizes on the performance of Arabic language models in downstream natural language processing tasks. Our investigation focused on the…

Adapting pretrained language models to low-resource, morphologically rich languages remains a significant challenge. Existing vocabulary expansion methods typically rely on arbitrarily segmented subword units, resulting in fragmented…

Recent large language models (LLMs) have achieved impressive reasoning milestones but continue to struggle with high computational costs, logical inconsistencies, and sharp performance degradation on high-complexity problems. While…

Morphologically-rich polysynthetic languages present a challenge for NLP systems due to data sparsity, and a common strategy to handle this issue is to apply subword segmentation. We investigate a wide variety of supervised and unsupervised…

Large language model (LLM) watermarking has emerged as a promising approach for detecting and attributing AI-generated text, yet its robustness to black-box spoofing remains insufficiently evaluated. Existing evaluation methods often demand…

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…

Fine-tuning LLMs for classification typically maps inputs directly to labels. We ask whether attaching brief explanations to each label during fine-tuning yields better models. We evaluate conversational response quality along three axes:…

An important assumption that comes with using LLMs on psycholinguistic data has gone unverified. LLM-based predictions are based on subword tokenization, not decomposition of words into morphemes. Does that matter? We carefully test this by…

Building a large image dataset with high-quality object masks for semantic segmentation is costly and time consuming. In this paper, we introduce a principled semi-supervised framework that only uses a small set of fully supervised images…

Machine translation tools do not yet exist for the Yup'ik language, a polysynthetic language spoken by around 8,000 people who live primarily in Southwest Alaska. We compiled a parallel text corpus for Yup'ik and English and developed a…

Large language model (LLM) tokenizers act as structured compressors: by mapping text to discrete token sequences, they determine token count (and thus compute and context usage) and the statistical structure seen by downstream models.…

Phonemization is a critical component in text-to-speech synthesis. Traditional approaches rely on deterministic transformations and lexica, while neural methods offer potential for higher generalization on out-of-vocabulary (OOV) terms.…

This work investigates how effectively large language models (LLMs) and their tokenization schemes represent and generate Arabic root-pattern morphology, probing whether they capture genuine morphological structure or rely on surface…