Related papers: Transformer Encoder for Social Science
Named entity recognition (NER) models generally perform poorly when large training datasets are unavailable for low-resource domains. Recently, pre-training a large-scale language model has become a promising direction for coping with the…
This paper proposes a transformer over transformer framework, called Transformer$^2$, to perform neural text segmentation. It consists of two components: bottom-level sentence encoders using pre-trained transformers, and an upper-level…
Recent studies on domain-specific BERT models show that effectiveness on downstream tasks can be improved when models are pretrained on in-domain data. Often, the pretraining data used in these models are selected based on their subject…
Text readability assessment has a wide range of applications for different target people, from language learners to people with disabilities. The fast pace of textual content production on the web makes it impossible to measure text…
The Transformer architecture deeply changed the natural language processing, outperforming all previous state-of-the-art models. However, well-known Transformer models like BERT, RoBERTa, and GPT-2 require a huge compute budget to create a…
Applying deep learning and computational intelligence to finance has been a popular area of applied research, both within academia and industry, and continues to attract active attention. The inherently high volatility and non-stationary of…
This paper investigates efficient methods for utilizing text-only data to improve speech recognition, focusing on encoder-dominated models that facilitate faster recognition. We provide a comprehensive comparison of techniques to integrate…
BERT achieves remarkable results in text classification tasks, it is yet not fully exploited, since only the last layer is used as a representation output for downstream classifiers. The most recent studies on the nature of linguistic…
The ubiquity of the contemporary language understanding tasks gives relevance to the development of generalized, yet highly efficient models that utilize all knowledge, provided by the data source. In this work, we present SocialBERT - the…
With the growth of the academic engines, the mining and analysis acquisition of massive researcher data, such as collaborator recommendation and researcher retrieval, has become indispensable. It can improve the quality of services and…
Automatic speech recognition (ASR) systems developed in recent years have shown promising results with self-attention models (e.g., Transformer and Conformer), which are replacing conventional recurrent neural networks. Meanwhile, a…
Pre-trained encoder-decoder transformer architectures have become increasingly popular recently with the advent of T5 models. T5 has also become more favorable over other architectures like BERT due to the amount of data that it is…
Much information available to applied researchers is contained within written language or spoken text. Deep language models such as BERT have achieved unprecedented success in many applications of computational linguistics. However, much…
Semantic similarity analysis and modeling is a fundamentally acclaimed task in many pioneering applications of natural language processing today. Owing to the sensation of sequential pattern recognition, many neural networks like RNNs and…
This paper investigates fake news detection as a downstream evaluation of Transformer representations, benchmarking encoder-only and decoder-only pre-trained models (BERT, GPT-2, Transformer-XL) as frozen embedders paired with lightweight…
Transformer models have shown impressive performance on a variety of NLP tasks. Off-the-shelf, pre-trained models can be fine-tuned for specific NLP classification tasks, reducing the need for large amounts of additional training data.…
Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and, thus, are too resource-hungry and…
Even though BERT achieves successful performance improvements in various supervised learning tasks, applying BERT for unsupervised tasks still holds a limitation that it requires repetitive inference for computing contextual language…
Image-text matching is an interesting and fascinating task in modern AI research. Despite the evolution of deep-learning-based image and text processing systems, multi-modal matching remains a challenging problem. In this work, we consider…
Developing high-performance entity normalization algorithms that can alleviate the term variation problem is of great interest to the biomedical community. Although deep learning-based methods have been successfully applied to biomedical…