We present a multilingual Named Entity Recognition approach based on a robust and
general set of features across languages and datasets. Our system combines shallow local …

We propose a simple and effective method for machine translation evaluation which does
not require reference translations. Our approach is based on (1) grounding the entity …

In order to control computational complexity, neural machine translation (NMT) systems
convert all rare words outside the vocabulary into a single unk symbol. Previous solution …

Automatic translation systems are known to struggle with rare words. Among these, named
entities (NEs) and domain-specific terms are crucial, since errors in their translation can lead …

In a sentence, certain words are critical for its semantic. Among them, named entities (NEs)
are notoriously challenging for neural models. Despite their importance, their accurate …

Foreign name transliterations typically include multiple spelling variants. These variants
cause data sparseness and inconsistency problems, increase the Out-of-Vocabulary (OOV) …

This PhD thesis summarizes the results of a three-year comprehensive investigation into the
dynamic domain of speech translation (ST), with a specific emphasis on application …

This paper argues in favor of a linguisticallyinformed error classification for SMT to identify
system weaknesses and map them to possible syntactic, semantic and structural fixes. We …

Рассматриваются вопросы передачи имён собственных в машинном переводе,
описаны подходы к передаче имён собственных, а также проблемы, возникающие при …

Information extraction (IE) is a challenging and essential task in the area of natural language
processing (NLP), and can be applied to a broad range of applications such as question …