Related papers: Comparison of Grammatical Error Correction Using B…
GPT-3 and GPT-4 models are powerful, achieving high performance on a variety of Natural Language Processing tasks. However, there is a relative lack of detailed published analysis of their performance on the task of grammatical error…
Large Language Models (LLMs) perform exceedingly well in Natural Language Understanding (NLU) tasks for many languages including English. However, despite being the fifth most-spoken language globally, Grammatical Error Correction (GEC) in…
Grammatical error correction (GEC) is a task dedicated to rectifying texts with minimal edits, which can be decoupled into two components: detection and correction. However, previous works have predominantly focused on direct correction,…
Neural Machine Translation has achieved state-of-the-art performance for several language pairs using a combination of parallel and synthetic data. Synthetic data is often generated by back-translating sentences randomly sampled from…
Grammatical Error Correction (GEC) and grammatical acceptability judgment (COLA) are core tasks in natural language processing, sharing foundational grammatical knowledge yet typically evolving independently. This paper introduces COLA-GEC,…
We propose a novel language-independent approach to improve the efficiency for Grammatical Error Correction (GEC) by dividing the task into two subtasks: Erroneous Span Detection (ESD) and Erroneous Span Correction (ESC). ESD identifies…
Grammar error correction (GEC) systems have become ubiquitous in a variety of software applications, and have started to approach human-level performance for some datasets. However, very little is known about how to efficiently personalize…
This paper proposes Transducers with Pronunciation-aware Embeddings (PET). Unlike conventional Transducers where the decoder embeddings for different tokens are trained independently, the PET model's decoder embedding incorporates shared…
Pre-training (PT) and back-translation (BT) are two simple and powerful methods to utilize monolingual data for improving the model performance of neural machine translation (NMT). This paper takes the first step to investigate the…
Recent work on non-autoregressive neural machine translation (NAT) aims at improving the efficiency by parallel decoding without sacrificing the quality. However, existing NAT methods are either inferior to Transformer or require multiple…
A prerequisite for training corpus-based machine translation (MT) systems -- either Statistical MT (SMT) or Neural MT (NMT) -- is the availability of high-quality parallel data. This is arguably more important today than ever before, as NMT…
While large-scale language models (LLMs) have demonstrated remarkable capabilities in specific natural language processing (NLP) tasks, they may still lack proficiency compared to specialized models in certain domains, such as grammatical…
Numerous domain-specific machine learning tasks struggle with data scarcity and class imbalance. This paper systematically explores data augmentation methods for NLP, particularly through large language models like GPT. The purpose of this…
The paper benchmarks several Transformer models [4], to show how these models can judge sentiment from a news event. This signal can then be used for downstream modelling and signal identification for commodity trading. We find that…
Chinese Grammatical Error Correction (CGEC) aims to generate a correct sentence from an erroneous sequence, where different kinds of errors are mixed. This paper divides the CGEC task into two steps, namely spelling error correction and…
We investigate the effectiveness of GPT-3.5 and GPT-4, two large language models, as Grammatical Error Correction (GEC) tools for Brazilian Portuguese and compare their performance against Microsoft Word and Google Docs. We introduce a GEC…
The overreliance on large parallel corpora significantly limits the applicability of machine translation systems to the majority of language pairs. Back-translation has been dominantly used in previous approaches for unsupervised neural…
Compared with only using limited authentic parallel data as training corpus, many studies have proved that incorporating synthetic parallel data, which generated by back translation (BT) or forward translation (FT, or selftraining), into…
Recent works have shown that synthetic parallel data automatically generated by translation models can be effective for various neural machine translation (NMT) issues. In this study, we build NMT systems using only synthetic parallel data.…
Back-translation (BT) of target monolingual corpora is a widely used data augmentation strategy for neural machine translation (NMT), especially for low-resource language pairs. To improve effectiveness of the available BT data, we…