Contextual word representations derived from large-scale neural language models are
successful across a diverse set of NLP tasks, suggesting that they encode useful and …

Natural Language Processing (NLP) helps empower intelligent machines by enhancing a
better understanding of the human language for linguistic-based human-computer …

With the starting point that implicit human biases are reflected in the statistical regularities of
language, it is possible to measure biases in English static word embeddings. State-of-the …

Compared to traditional machine learning, deep learning can learn deeper abstract data
representation and understand scattered data properties. It has gained considerable …

Data augmentation techniques have been widely used to improve machine learning
performance as they enhance the generalization capability of models. In this work, to …

Sequence labeling (SL) is a fundamental research problem encompassing a variety of tasks,
eg, part-of-speech (POS) tagging, named entity recognition (NER), text chunking, etc …

Narratives are present in many forms of human expression and can be understood as a
fundamental way of communication between people. Computational understanding of the …

Most pre-trained language models (PLMs) construct word representations at subword level
with Byte-Pair Encoding (BPE) or its variations, by which OOV (out-of-vocab) words are …

We propose a practical scheme to train a single multilingual sequence labeling model that
yields state of the art results and is small and fast enough to run on a single CPU. Starting …

We use the multilingual OSCAR corpus, extracted from Common Crawl via language
classification, filtering and cleaning, to train monolingual contextualized word embeddings …