This article surveys work on Unsupervised Learning of Morphology. We define
Unsupervised Learning of Morphology as the problem of inducing a description (of some …

Subword segmentation is widely used to address the open vocabulary problem in machine
translation. The dominant approach to subword segmentation is Byte Pair Encoding (BPE) …

This work presents an algorithm for the unsupervised learning, or induction, of a simple
morphology of a natural language. A probabilistic maximum a posteriori model is utilized …

We propose task-adaptive tokenization as a way to adapt the generation pipeline to the
specifics of a downstream task and enhance long-form generation in mental health. Inspired …

We explore the use of two independent subsystems Byte Pair Encoding (BPE) and
Morfessor as basic units for subword-level neural machine translation (NMT). We show that …

This paper extends the training and tuning regime for phrase-based statistical machine
translation to obtain fluent translations into morphologically complex languages (we build an …

In order to develop computer applications that successfully process natural language data
(text and speech), one needs good models of the vocabulary and grammar of as many …

This paper presents the evaluation of Morpho Challenge Competition 1 (linguistic gold
standard). The Competition 2 (information retrieval) is described in a companion paper. In …

This study examines the cross-linguistic potential for the automatic analysis of verbal
morphology and creation of implemented formal grammars using the Grammar Matrix …

In this paper, we present TituLLMs, the first large pretrained Bangla LLMs, available in 1B
and 3B parameter sizes. Due to computational constraints during both training and …