Related papers: UniMorph 4.0: Universal Morphology

The traditional approach to morphological inflection (the task of modifying a base word (lemma) to express grammatical categories) has been, for decades, to consider lexical entries of lemma-tag-form triples uniformly, lacking any…

In the domain of Morphology, Inflection is a fundamental and important task that gained a lot of traction in recent years, mostly via SIGMORPHON's shared-tasks. With average accuracy above 0.9 over the scores of all languages, the task is…

Morphological segmentation has traditionally been modeled with non-hierarchical models, which yield flat segmentations as output. In many cases, however, proper morphological analysis requires hierarchical structure -- especially in the…

Modern work on the cross-linguistic computational modeling of morphological inflection has typically employed language-independent data splitting algorithms. In this paper, we supplement that approach with language-specific probes designed…

The SIGMORPHON 2022 shared task on morpheme segmentation challenged systems to decompose a word into a sequence of morphemes and covered most types of morphology: compounds, derivations, and inflections. Subtask 1, word-level morpheme…

Morphologically rich languages accentuate two properties of distributional vector space models: 1) the difficulty of inducing accurate representations for low-frequency word forms; and 2) insensitivity to distinct lexical relations that…

We propose to cast the task of morphological inflection - mapping a lemma to an indicated inflected form - for resource-poor languages as a meta-learning problem. Treating each language as a separate task, we use data from high-resource…

The modern technological landscape has trended towards increased precision and greater digitization of information. However, the methods used to record and communicate scientific procedures have remained largely unchanged over the last…

We quantify the linguistic complexity of different languages' morphological systems. We verify that there is an empirical trade-off between paradigm size and irregularity: a language's inflectional paradigms may be either large in size or…

This paper presents UniBERT, a compact multilingual language model that uses an innovative training framework that integrates three components: masked language modeling, adversarial training, and knowledge distillation. Pre-trained on a…

We generalized a voice morphing algorithm capable of handling temporally variable, multiple-attributes, and multiple instances. The generalized morphing provides a new strategy for investigating speech diversity. However, excessive…

We train neural models for morphological analysis, generation and lemmatization for morphologically rich languages. We present a method for automatically extracting substantially large amount of training data from FSTs for 22 languages, out…

We present FreeMorph, the first tuning-free method for image morphing that accommodates inputs with different semantics or layouts. Unlike existing methods that rely on finetuning pre-trained diffusion models and are limited by time…

Model editing aims to enhance the accuracy and reliability of large language models (LLMs) by efficiently adjusting their internal parameters. Currently, most LLM editing datasets are confined to narrow knowledge domains and cover a limited…

Multimodal large language models (MLLMs) have gained significant attention due to their strong multimodal understanding capability. However, existing works rely heavily on modality-specific encoders, which usually differ in architecture and…

Linguistic analysis of language models is one of the ways to explain and describe their reasoning, weaknesses, and limitations. In the probing part of the model interpretability research, studies concern individual languages as well as…

The advancement of artificial intelligence (AI) for organ segmentation and tumor detection is propelled by the growing availability of computed tomography (CT) datasets with detailed, per-voxel annotations. However, these AI models often…

The use of subword-level information (e.g., characters, character n-grams, morphemes) has become ubiquitous in modern word representation learning. Its importance is attested especially for morphologically rich languages which generate a…

In scientific research and its application, scientific literature analysis is crucial as it allows researchers to build on the work of others. However, the fast growth of scientific knowledge has led to a massive increase in scholarly…

Recent advances in multilingual dependency parsing have brought the idea of a truly universal parser closer to reality. However, cross-language interference and restrained model capacity remain major obstacles. To address this, we propose a…