Despite the recent success of deep neural networks in natural language processing and
other spheres of artificial intelligence, their interpretability remains a challenge. We analyze …

With the development of high computational devices, deep neural networks (DNNs), in
recent years, have gained significant popularity in many Artificial Intelligence (AI) …

Multilingual BERT (mBERT) trained on 104 languages has shown surprisingly good cross-
lingual performance on several NLP tasks, even without explicit cross-lingual signals …

UDPipe is a trainable pipeline which performs sentence segmentation, tokenization, POS
tagging, lemmatization and dependency parsing. We present a prototype for UDPipe 2.0 …

Viable cross-lingual transfer critically depends on the availability of parallel texts. Shortage
of such resources imposes a development and evaluation bottleneck in multilingual …

A key component of research on human sentence processing is to characterize the
processing difficulty associated with the comprehension of words in context. Models that …

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 …

Non-task oriented dialogue systems have achieved great success in recent years due to
largely accessible conversation data and the development of deep learning techniques …

Neural NLP systems achieve high scores in the presence of sizable training dataset. Lack of
such datasets leads to poor system performances in the case low-resource languages. We …

Multilingual Language Models (\MLLMs) such as mBERT, XLM, XLM-R,\textit {etc.} have
emerged as a viable option for bringing the power of pretraining to a large number of …