Related papers: Larth: Dataset and Machine Translation for Etrusca…

This paper surveys 60 English Machine Reading Comprehension datasets, with a view to providing a convenient resource for other researchers interested in this problem. We categorize the datasets according to their question and answer form…

Pronunciation is one of the fundamentals of language learning, and it is considered a primary factor of spoken language when it comes to an understanding and being understood by others. The persistent presence of high error rates in speech…

Pre-trained language models have revolutionized the natural language understanding landscape, most notably BERT (Bidirectional Encoder Representations from Transformers). However, a significant challenge remains for low-resource languages,…

This paper presents EstBERT, a large pretrained transformer-based language-specific BERT model for Estonian. Recent work has evaluated multilingual BERT models on Estonian tasks and found them to outperform the baselines. Still, based on…

As premodern texts are passed down over centuries, errors inevitably accrue. These errors can be challenging to identify, as some have survived undetected for so long precisely because they are so elusive. While prior work has evaluated…

Machine Translation (MT) is an area in natural language processing, which focus on translating from one language to another. Many approaches ranging from statistical methods to deep learning approaches are used in order to achieve MT.…

Language documentation projects often involve the creation of annotated text in a format such as interlinear glossed text (IGT), which captures fine-grained morphosyntactic analyses in a morpheme-by-morpheme format. However, there are few…

In this chapter we build a machine translation (MT) system tailored to the literary domain, specifically to novels, based on the state-of-the-art architecture in neural MT (NMT), the Transformer (Vaswani et al., 2017), for the translation…

In this paper, we investigate the problem of training neural machine translation (NMT) systems with a dataset of more than 40 billion bilingual sentence pairs, which is larger than the largest dataset to date by orders of magnitude.…

We present FRMT, a new dataset and evaluation benchmark for Few-shot Region-aware Machine Translation, a type of style-targeted translation. The dataset consists of professional translations from English into two regional variants each of…

There is a lack of research into capabilities of recent LLMs to generate convincing text in languages other than English and into performance of detectors of machine-generated text in multilingual settings. This is also reflected in the…

In this paper, SER_AMPEL, a multi-source dataset for speech emotion recognition (SER) is presented. The peculiarity of the dataset is that it is collected with the aim of providing a reference for speech emotion recognition in case of…

Unlike classical lexical overlap metrics such as BLEU, most current evaluation metrics for machine translation (for example, COMET or BERTScore) are based on black-box large language models. They often achieve strong correlations with human…

The oldest (c. 4000 BC) undeciphered language is the Old European Script known from approximately 940 inscribed objects (82% of inscriptions on pottery) found in excavations in the Vinca-Tordos region Transylvania. Also, it is not known for…

English pretrained language models, which make up the backbone of many modern NLP systems, require huge amounts of unlabeled training data. These models are generally presented as being trained only on English text but have been found to…

This works aims to design a statistical machine translation from English text to American Sign Language (ASL). The system is based on Moses tool with some modifications and the results are synthesized through a 3D avatar for interpretation.…

In this paper, we propose to extend the recently introduced model-agnostic meta-learning algorithm (MAML) for low-resource neural machine translation (NMT). We frame low-resource translation as a meta-learning problem, and we learn to adapt…

Machine-translated benchmark datasets reduce costs and offer scale, but noise, loss of structure, and uneven quality weaken confidence. What matters is not merely whether we can translate, but also whether we can measure and verify…

Neural Machine Translation (NMT) for low-resource languages is still a challenging task in front of NLP researchers. In this work, we deploy a standard data augmentation methodology by back-translation to a new language translation…

How can large language models (LLMs) process and translate endangered languages? Many languages lack a large corpus to train a decent LLM; therefore existing LLMs rarely perform well in unseen, endangered languages. On the contrary, we…