Related papers: An Analysis of Language Frequency and Error Correc…

Thanks to recent advances in generative AI, we are able to prompt large language models (LLMs) to produce texts which are fluent and grammatical. In addition, it has been shown that we can elicit attempts at grammatical error correction…

This study evaluates the potential of ChatGPT-4, an artificial intelligence language model developed by OpenAI, as an editing tool for Spanish literary and academic books. The need for efficient and accessible reviewing and editing…

ChatGPT has demonstrated impressive performance in various downstream tasks. However, in the Chinese Spelling Correction (CSC) task, we observe a discrepancy: while ChatGPT performs well under human evaluation, it scores poorly according to…

Recent studies have demonstrated promising performance of ChatGPT and GPT-4 on several medical domain tasks. However, none have assessed its performance using a large-scale real-world electronic health record database, nor have evaluated…

The proliferation of sexually explicit content in popular music genres such as reggaeton and trap, consumed predominantly by young audiences, has raised significant societal concern regarding the exposure of minors to potentially harmful…

Generative Error Correction (GEC) has emerged as a powerful post-processing method to enhance the performance of Automatic Speech Recognition (ASR) systems. However, we show that GEC models struggle to generalize beyond the specific types…

The Spanish language is one of the top 5 spoken languages in the world. Nevertheless, finding resources to train or evaluate Spanish language models is not an easy task. In this paper we help bridge this gap by presenting a BERT-based…

Automatic Speech Recognition (ASR) systems struggle with child speech due to its distinct acoustic and linguistic variability and limited availability of child speech datasets, leading to high transcription error rates. While ASR error…

Large language models require vast amounts of high-quality training data, but effective filtering of web-scale datasets remains a significant challenge. This paper demonstrates that GPT-4o is remarkably effective at identifying high-quality…

We present a large-scale study of linguistic bias exhibited by ChatGPT covering ten dialects of English (Standard American English, Standard British English, and eight widely spoken non-"standard" varieties from around the world). We…

Large-scale language models (LLMs) has shown remarkable capability in various of Natural Language Processing (NLP) tasks and attracted lots of attention recently. However, some studies indicated that large language models fail to achieve…

Text simplification, crucial in natural language processing, aims to make texts more comprehensible, particularly for specific groups like visually impaired Spanish speakers, a less-represented language in this field. In Spanish, there are…

Even in highly-developed countries, as many as 15-30\% of the population can only understand texts written using a basic vocabulary. Their understanding of everyday texts is limited, which prevents them from taking an active role in society…

Some grammatical error correction (GEC) systems incorporate hand-crafted rules and achieve positive results. However, manually defining rules is time-consuming and laborious. In view of this, we propose a method to mine error templates for…

We extend a current sequence-tagging approach to Grammatical Error Correction (GEC) by introducing specialised tags for spelling correction and morphological inflection using the SymSpell and LemmInflect algorithms. Our approach improves…

Language models often pre-train on large unsupervised text corpora, then fine-tune on additional task-specific data. However, typical fine-tuning schemes do not prioritize the examples that they tune on. We show that, if you can prioritize…

The rapid advancement of Large Language Models (LLMs) in the realm of mathematical reasoning necessitates comprehensive evaluations to gauge progress and inspire future directions. Existing assessments predominantly focus on problem-solving…

The incorporation of pseudo data in the training of grammatical error correction models has been one of the main factors in improving the performance of such models. However, consensus is lacking on experimental configurations, namely,…

With the rise of globalisation, code-switching (CSW) has become a ubiquitous part of multilingual conversation, posing new challenges for natural language processing (NLP), especially in Grammatical Error Correction (GEC). This work…

In the last few years, pre-trained neural architectures have provided impressive improvements across several NLP tasks. Still, generative language models are available mainly for English. We develop GePpeTto, the first generative language…