Related papers: Data Weighted Training Strategies for Grammatical …

Error correction (EC) based on large language models is an emerging technology to enhance the performance of automatic speech recognition (ASR) systems. Generally, training data for EC are collected by automatically pairing a large set of…

Semantically meaningful sentence embeddings are important for numerous tasks in natural language processing. To obtain such embeddings, recent studies explored the idea of utilizing synthetically generated data from pretrained language…

Although large language models demonstrate strong performance across various domains, they still struggle with numerous bad cases in mathematical reasoning. Previous approaches to learning from errors synthesize training data by solely…

Identifying and correcting grammatical errors in the text written by non-native writers has received increasing attention in recent years. Although a number of annotated corpora have been established to facilitate data-driven grammatical…

In grammatical error correction (GEC), automatic evaluation is an important factor for research and development of GEC systems. Previous studies on automatic evaluation have demonstrated that quality estimation models built from datasets…

Synthetic data augmentation via large language models (LLMs) allows researchers to leverage additional training data, thus enhancing the performance of downstream tasks, especially when real-world data is scarce. However, the generated data…

This paper describes our approach to hierarchical multi-label detection of persuasion techniques in meme texts. Our model, developed as a part of the recent SemEval task, is based on fine-tuning individual language models (BERT,…

This research introduces KoGEC, a Korean Grammatical Error Correction system using pre\--trained translation models. We fine-tuned NLLB (No Language Left Behind) models for Korean GEC, comparing their performance against large language…

Automatic Speech Recognition (ASR) systems have demonstrated remarkable performance across various applications. However, limited data and the unique language features of specific domains, such as low-resource languages, significantly…

As artificial neural networks, and specifically large language models, have improved rapidly in capabilities and quality, they have increasingly been deployed in real-world applications, from customer service to Google search, despite the…

It is known that a deep neural network model pre-trained with large-scale data greatly improves the accuracy of various tasks, especially when there are resource constraints. However, the information needed to solve a given task can vary,…

Multimodal reward models are crucial for aligning multimodal large language models with human preferences. Recent works have incorporated reasoning capabilities into these models, achieving promising results. However, training these models…

As research on machine translation moves to translating text beyond the sentence level, it remains unclear how effective automatic evaluation metrics are at scoring longer translations. In this work, we first propose a method for creating…

Grammatical Error Correction (GEC) relies on accurate error annotation and evaluation, yet existing frameworks, such as $\texttt{errant}$, face limitations when extended to typologically diverse languages. In this paper, we introduce a…

We propose a training-free approach to improve sentence embeddings leveraging test-time compute by applying generative text models for data augmentation at inference time. Unlike conventional data augmentation that utilises synthetic…

Given recent advances in generative AI technology, a key question is how large language models (LLMs) can enhance acoustic modeling tasks using text decoding results from a frozen, pretrained automatic speech recognition (ASR) model. To…

We develop a methodology for analyzing language model task performance at the individual example level based on training data density estimation. Experiments with paraphrasing as a controlled intervention on finetuning data demonstrate that…

Despite strong performance in data-rich regimes, deep learning often underperforms in the data-scarce settings common in practice. While foundation models (FMs) trained on massive datasets demonstrate strong generalization by extracting…

Data augmentation techniques are widely used for enhancing the performance of machine learning models by tackling class imbalance issues and data sparsity. State-of-the-art generative language models have been shown to provide significant…

Pre-trained language models (PLMs) show impressive performance in various downstream NLP tasks. However, pre-training large language models demands substantial memory and training compute. Furthermore, due to the substantial resources…