Related papers: Correct Like Humans: Progressive Learning Framewor…

Large Language Models (LLMs) have demonstrated substantial potential for error correction in Automatic Speech Recognition (ASR). However, most research focuses on utterances from short-duration speech recordings, which are the predominant…

Although existing neural network approaches have achieved great success on Chinese spelling correction, there is still room to improve. The model is required to avoid over-correction and to distinguish a correct token from its phonological…

Recently, large language models (LLMs) are capable of generating highly fluent textual content. While they offer significant convenience to humans, they also introduce various risks, like phishing and academic dishonesty. Numerous research…

This paper aims to advance the mathematical intelligence of machines by presenting the first Chinese mathematical pre-trained language model~(PLM) for effectively understanding and representing mathematical problems. Unlike other standard…

Scene text recognition has been studied for decades due to its broad applications. However, despite Chinese characters possessing different characteristics from Latin characters, such as complex inner structures and large categories, few…

Large language models (LLMs) have significantly advanced natural language processing, particularly through the integration of external tools and APIs. However, their effectiveness is frequently hampered by parameter mis-filling during tool…

Recent research efforts have investigated how to integrate Large Language Models (LLMs) into recommendation, capitalizing on their semantic comprehension and open-world knowledge for user behavior understanding. These approaches…

While recent code-specific large language models (LLMs) have greatly enhanced their code generation capabilities, the safety of these models remains under-explored, posing potential risks as insecure code generated by these models may…

Chinese Spell Checking (CSC) task aims to detect and correct Chinese spelling errors. Recently, related researches focus on introducing character similarity from confusion set to enhance the CSC models, ignoring the context of characters…

Recent researches show that pre-trained models (PTMs) are beneficial to Chinese Word Segmentation (CWS). However, PTMs used in previous works usually adopt language modeling as pre-training tasks, lacking task-specific prior segmentation…

Chinese Spelling Correction (CSC) aims to detect and correct spelling errors in given sentences. Recently, multi-domain CSC has gradually attracted the attention of researchers because it is more practicable. In this paper, we focus on the…

This thesis addresses automatic lexical error recovery and tokenization of corrupt text input. We propose a technique that can automatically correct misspellings, segmentation errors and real-word errors in a unified framework that uses…

Small Language Models (SLMs) enable cost-effective, on-device and latency-sensitive AI applications, yet their deployment in Traditional Chinese (TC) remains hindered by token-level instability - models unpredictably emit non-TC characters…

Large language models (LLMs) recently exhibited remarkable reasoning capabilities on solving math problems. To further improve their reasoning capabilities, this work explores whether LLMs can LEarn from MistAkes (LEMA), akin to the human…

Synthetic data construction of Grammatical Error Correction (GEC) for non-English languages relies heavily on human-designed and language-specific rules, which produce limited error-corrected patterns. In this paper, we propose a generic…

Video-and-language pre-training has shown promising improvements on various downstream tasks. Most previous methods capture cross-modal interactions with a transformer-based multimodal encoder, not fully addressing the misalignment between…

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…

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…

Traditional Chinese Medicine (TCM) theory is built on imagistic thinking, in which medical principles and diagnostic and therapeutic logic are structured through metaphor and metonymy. However, existing English translations largely rely on…

Grammatical Error Correction (GEC) faces a critical challenge concerning explainability, notably when GEC systems are designed for language learners. Existing research predominantly focuses on explaining grammatical errors extracted in…