Related papers: Scrambled text: training Language Models to correc…
Large language models (LLMs) have shown impressive promise in code generation, yet their progress remains limited by the shortage of large-scale datasets that are both diverse and well-aligned with human reasoning. Most existing resources…
Despite recent progress in text-to-SQL parsing, current semantic parsers are still not accurate enough for practical use. In this paper, we investigate how to build automatic text-to-SQL error correction models. Noticing that token-level…
Instruction tuning has emerged as the key in aligning large language models (LLMs) with specific task instructions, thereby mitigating the discrepancy between the next-token prediction objective and users' actual goals. To reduce the labor…
The study investigates the potential of post-OCR models to overcome limitations in OCR models and explores the impact of incorporating glyph embedding on post-OCR correction performance. In this study, we have developed our own post-OCR…
Progress in neural grammatical error correction (GEC) is hindered by the lack of annotated training data. Sufficient amounts of high-quality manually annotated data are not available, so recent research has relied on generating synthetic…
Optical character recognition (OCR) is crucial for a deeper access to historical collections. OCR needs to account for orthographic variations, typefaces, or language evolution (i.e., new letters, word spellings), as the main source of…
Advances in NLP have yielded impressive results for the task of machine reading comprehension (MRC), with approaches having been reported to achieve performance comparable to that of humans. In this paper, we investigate whether…
Training on high-quality synthetic data from strong language models (LMs) is a common strategy to improve the reasoning performance of LMs. In this work, we revisit whether this strategy is compute-optimal under a fixed inference budget…
Discriminative pre-trained language models (PLMs) learn to predict original texts from intentionally corrupted ones. Taking the former text as positive and the latter as negative samples, the PLM can be trained effectively for…
Large language models (LLMs) can be leveraged to help with writing formulas in spreadsheets, but resources on these formulas are scarce, impacting both the base performance of pre-trained models and limiting the ability to fine-tune them.…
Collecting high-quality training data is essential for fine-tuning Large Language Models (LLMs). However, acquiring such data is often costly and time-consuming, especially for non-English languages such as Italian. Recently, researchers…
Document digitization is essential for the digital transformation of our societies, yet a crucial step in the process, Optical Character Recognition (OCR), is still not perfect. Even commercial OCR systems can produce questionable output…
In this paper we evaluate Optical Character Recognition (OCR) of 19th century Fraktur scripts without book-specific training using mixed models, i.e. models trained to recognize a variety of fonts and typesets from previously unseen…
The risk of harmful content generated by large language models (LLMs) becomes a critical concern. This paper presents a systematic study on assessing and improving LLMs' capability to perform the task of \textbf{course-correction}, \ie, the…
Automation of code reviews using AI models has garnered substantial attention in the software engineering community as a strategy to reduce the cost and effort associated with traditional peer review processes. These models are typically…
With the advent of digital optical scanners, a lot of paper-based books, textbooks, magazines, articles, and documents are being transformed into an electronic version that can be manipulated by a computer. For this purpose, OCR, short for…
An ongoing challenge in current natural language processing is how its major advancements tend to disproportionately favor resource-rich languages, leaving a significant number of under-resourced languages behind. Due to the lack of…
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…
Linked Data is used in various fields as a new way of structuring and connecting data. Cultural heritage institutions have been using linked data to improve archival descriptions and facilitate the discovery of information. Most archival…
High-quality, error-free datasets are a key ingredient in building reliable, accurate, and unbiased machine learning (ML) models. However, real world datasets often suffer from errors due to sensor malfunctions, data entry mistakes, or…