Related papers: Evaluation of contextual embeddings on less-resour…
Large pretrained masked language models have become state-of-the-art solutions for many NLP problems. While studies have shown that monolingual models produce better results than multilingual models, the training datasets must be…
Pre-trained contextualized embedding models such as BERT are a standard building block in many natural language processing systems. We demonstrate that the sentence-level representations produced by some off-the-shelf contextualized…
Exploiting large pretrained models for various NMT tasks have gained a lot of visibility recently. In this work we study how BERT pretrained models could be exploited for supervised Neural Machine Translation. We compare various ways to…
Recently, large pre-trained language models, such as BERT, have reached state-of-the-art performance in many natural language processing tasks, but for many languages, including Estonian, BERT models are not yet available. However, there…
Dense vector representations for textual data are crucial in modern NLP. Word embeddings and sentence embeddings estimated from raw texts are key in achieving state-of-the-art results in various tasks requiring semantic understanding.…
Multilingual BERT (M-BERT) has been a huge success in both supervised and zero-shot cross-lingual transfer learning. However, this success has focused only on the top 104 languages in Wikipedia that it was trained on. In this paper, we…
This paper presents new state-of-the-art models for three tasks, part-of-speech tagging, syntactic parsing, and semantic parsing, using the cutting-edge contextualized embedding framework known as BERT. For each task, we first replicate and…
Contextualized word embeddings, i.e. vector representations for words in context, are naturally seen as an extension of previous noncontextual distributional semantic models. In this work, we focus on BERT, a deep neural network that…
Building machine learning prediction models for a specific NLP task requires sufficient training data, which can be difficult to obtain for less-resourced languages. Cross-lingual embeddings map word embeddings from a less-resourced…
Advances in Natural Language Processing (NLP) have revolutionized the way researchers and practitioners address crucial societal problems. Large language models are now the standard to develop state-of-the-art solutions for text detection…
Transformers are the most eminent architectures used for a vast range of Natural Language Processing tasks. These models are pre-trained over a large text corpus and are meant to serve state-of-the-art results over tasks like text…
Neural network-based representations ("embeddings") have dramatically advanced natural language processing (NLP) tasks, including clinical NLP tasks such as concept extraction. Recently, however, more advanced embedding methods and…
This paper investigates the problem of learning cross-lingual representations in a contextual space. We propose Cross-Lingual BERT Transformation (CLBT), a simple and efficient approach to generate cross-lingual contextualized word…
The application of Natural Language Processing (NLP) has achieved a high level of relevance in several areas. In the field of software engineering (SE), NLP applications are based on the classification of similar texts (e.g. software…
In the natural language processing literature, neural networks are becoming increasingly deeper and complex. The recent poster child of this trend is the deep language representation model, which includes BERT, ELMo, and GPT. These…
Transformer-based language models have taken many fields in NLP by storm. BERT and its derivatives dominate most of the existing evaluation benchmarks, including those for Word Sense Disambiguation (WSD), thanks to their ability in…
Language models based on deep neural networks have facilitated great advances in natural language processing and understanding tasks in recent years. While models covering a large number of languages have been introduced, their…
The contextual word embedding model, BERT, has proved its ability on downstream tasks with limited quantities of annotated data. BERT and its variants help to reduce the burden of complex annotation work in many interdisciplinary research…
Models based on the transformer architecture, such as BERT, have marked a crucial step forward in the field of Natural Language Processing. Importantly, they allow the creation of word embeddings that capture important semantic information…
Recent works show that learning contextualized embeddings for words is beneficial for downstream tasks. BERT is one successful example of this approach. It learns embeddings by solving two tasks, which are masked language model (masked LM)…