What Matters Most in Morphologically Segmented SMT Models?

Tuning Phrase-Based Segmented Translation for a Morphologically Complex Target Language

Predictive text for agglutinative and polysynthetic languages

This paper presents a set of experiments in the area of morphological modelling and predictioning. We examine the tasks of segmentation and predictive text entry for two under-resourced and indigenous languages, K'iche'…

Predictive Text for Agglutinative and Polysynthetic Languages

This paper presents a set of experiments in the area of morphological modelling and prediction. We test whether morphological segmentation can compete against statistical segmentation in the tasks of language modelling a…

Words, Subwords, and Morphemes: What Really Matters in the Surprisal-Reading Time Relationship?

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 ca…

LGSE: Lexically Grounded Subword Embedding Initialization for Low-Resource Language Adaptation

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 …