Related papers: To Augment or Not to Augment? A Comparative Study …
The principal task in supervised neural machine translation (NMT) is to learn to generate target sentences conditioned on the source inputs from a set of parallel sentence pairs, and thus produce a model capable of generalizing to unseen…
Sentiment analysis plays a crucial role in understanding the sentiment expressed in text data. While sentiment analysis research has been extensively conducted in English and other Western languages, there exists a significant gap in…
Pretrained contextual and non-contextual subword embeddings have become available in over 250 languages, allowing massively multilingual NLP. However, while there is no dearth of pretrained embeddings, the distinct lack of systematic…
Text clustering is an important method for organising the increasing volume of digital content, aiding in the structuring and discovery of hidden patterns in uncategorised data. The effectiveness of text clustering largely depends on the…
The absence of large labeled datasets remains a significant challenge in many application areas of deep learning. Researchers and practitioners typically resort to transfer learning and data augmentation to alleviate this issue. We study…
End-to-end Speech Translation is hindered by a lack of available data resources. While most of them are based on documents, a sentence-level version is available, which is however single and static, potentially impeding the usefulness of…
Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific…
Foundational Language Models (FLMs) have advanced natural language processing (NLP) research. Current researchers are developing larger FLMs (e.g., XLNet, T5) to enable contextualized language representation, classification, and generation.…
Handwritten text and scene text suffer from various shapes and distorted patterns. Thus training a robust recognition model requires a large amount of data to cover diversity as much as possible. In contrast to data collection and…
This paper proposes a Clustering, Labeling, then Augmenting framework that significantly enhances performance in Semi-Supervised Text Classification (SSTC) tasks, effectively addressing the challenge of vast datasets with limited labeled…
Business Process Modeling projects often require formal process models as a central component. High costs associated with the creation of such formal process models motivated many different fields of research aimed at automated generation…
Real-world NLP applications often deal with nonstandard text (e.g., dialectal, informal, or misspelled text). However, language models like BERT deteriorate in the face of dialect variation or noise. How do we push BERT's modeling…
The rise of big data analytics on top of NLP increases the computational burden for text processing at scale. The problems faced in NLP are very high dimensional text, so it takes a high computation resource. The MapReduce allows…
Large Language Models (LLMs) are powerful models for generation tasks, but they may not generate good quality outputs in their first attempt. Apart from model fine-tuning, existing approaches to improve prediction accuracy and quality…
The introduction of Large Language Models (LLMs), and the vast volume of publicly available medical data, amplified the application of NLP to the medical domain. However, LLMs are pretrained on data that are not explicitly relevant to the…
Embedding models are crucial for various natural language processing tasks but can be limited by factors such as limited vocabulary, lack of context, and grammatical errors. This paper proposes a novel approach to improve embedding…
Data augmentation is an effective approach to tackle over-fitting. Many previous works have proposed different data augmentations strategies for NLP, such as noise injection, word replacement, back-translation etc. Though effective, they…
With the growth of the Internet, buying habits have changed, and customers have become more dependent on the online opinions of other customers to guide their purchases. Identifying fake reviews thus became an important area for Natural…
Data augmentation has been widely used in low-resource NER tasks to tackle the problem of data sparsity. However, previous data augmentation methods have the disadvantages of disrupted syntactic structures, token-label mismatch, and…
In this paper, we explore Annotation Artifacts - the phenomena wherein large pre-trained NLP models achieve high performance on benchmark datasets but do not actually "solve" the underlying task and instead rely on some dataset artifacts…