Related papers: Hybrid lemmatization in HuSpaCy
Training summarization models requires substantial amounts of training data. However for less resourceful languages like Hungarian, openly available models and datasets are notably scarce. To address this gap our paper introduces HunSum-2…
Different from the traditional classification tasks which assume mutual exclusion of labels, hierarchical multi-label classification (HMLC) aims to assign multiple labels to every instance with the labels organized under hierarchical…
With multilingual machine translation (MMT) models continuing to grow in size and number of supported languages, it is natural to reuse and upgrade existing models to save computation as data becomes available in more languages. However,…
Code-mixed discourse combines multiple languages in a single text. It is commonly used in informal discourse in countries with several official languages, but also in many other countries in combination with English or neighboring…
Since their inception, embeddings have become a primary ingredient in many flavours of Natural Language Processing (NLP) tasks supplanting earlier types of representation. Even though multilingual embeddings have been used for the…
Towards developing high-performing ASR for low-resource languages, approaches to address the lack of resources are to make use of data from multiple languages, and to augment the training data by creating acoustic variations. In this work…
This paper describes our submission to CoNLL 2018 UD Shared Task. We have extended an LSTM-based neural network designed for sequence tagging to additionally generate character-level sequences. The network was jointly trained to produce…
Training automatic speech recognition (ASR) models increasingly relies on decentralized federated learning to ensure data privacy and accessibility, producing multiple local models that require effective merging. In hybrid ASR systems,…
Natural language generation systems (NLG) map non-linguistic representations into strings of words through a number of steps using intermediate representations of various levels of abstraction. Template based systems, by contrast, tend to…
Modern statistical machine translation (SMT) systems usually use a linear combination of features to model the quality of each translation hypothesis. The linear combination assumes that all the features are in a linear relationship and…
In the era of diminishing returns from Moores Law, heterogeneous computing systems have emerged as a vital approach to enhance computational efficiency. This paper introduces a novel MLIR-based dialect, named hyper, designed to optimize…
This paper explores proof-theoretic aspects of hybrid type-logical grammars , a logic combining Lambek grammars with lambda grammars. We prove some basic properties of the calculus, such as normalisation and the subformula property and also…
Automating legal reasoning forces a choice between imperfect alternatives: symbolic systems offer transparency but struggle with ambiguity, whereas neural systems handle natural language flexibly but lack verifiability. This paper…
Syllables play an important role in speech synthesis, speech recognition, and spoken document retrieval. A novel, low cost, and language agnostic approach to dividing words into their corresponding syllables is presented. A hybrid genetic…
This paper introduces LatinCy, a set of trained general purpose Latin-language "core" pipelines for use with the spaCy natural language processing framework. The models are trained on a large amount of available Latin data, including all…
Bilingual word embeddings have been widely used to capture the similarity of lexical semantics in different human languages. However, many applications, such as cross-lingual semantic search and question answering, can be largely benefited…
Across languages, numeral systems vary widely in how they construct and combine numbers. While humans consistently learn to navigate this diversity, large language models (LLMs) struggle with linguistic-mathematical puzzles involving…
Low-resource indigenous languages often lack the parallel corpora required for effective neural machine translation (NMT). Synthetic data generation offers a practical strategy for mitigating this limitation in data-scarce settings. In this…
We present Racka, a lightweight, continually pretrained large language model designed to bridge the resource gap between Hungarian and high-resource languages such as English and German. Racka employs parameter-efficient continual…
Neural Machine Translation (NMT) models generally perform translation using a fixed-size lexical vocabulary, which is an important bottleneck on their generalization capability and overall translation quality. The standard approach to…