The rapid growth of Internet-based applications, such as social media platforms and blogs,
has resulted in comments and reviews concerning day-to-day activities. Sentiment analysis …

How to feed the world is a vigorously debated question, but the extent to which possible
solutions receive attention in the scientific literature has not been studied. Using textual …

In this work, we provide a systematic and comprehensive empirical comparison of pretrained
multilingual language models versus their monolingual counterparts with regard to their …

Many natural language processing tasks, including the most advanced ones, routinely start
by several basic processing steps–tokenization and segmentation, most likely also POS …

This paper describes the development of a new benchmark for machine translation that
provides training and test data for thousands of language pairs covering over 500 …

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

Ancient languages preserve the cultures and histories of the past. However, their study is
fraught with difficulties, and experts must tackle a range of challenging text-based tasks, from …

This paper describes our system (HIT-SCIR) submitted to the CoNLL 2018 shared task on
Multilingual Parsing from Raw Text to Universal Dependencies. We base our submission on …

Pretrained language models have been shown to encode relational information, such as the
relations between entities or concepts in knowledge-bases--(Paris, Capital, France) …

This paper describes the neural dependency parser submitted by Stanford to the CoNLL
2017 Shared Task on parsing Universal Dependencies. Our system uses relatively simple …