Контекстуализированные векторы

AbstractMultilingual BERT (mBERT) has shown reasonable capability for zero-shot cross-lingual transfer when fine-tuned on downstream tasks. Since mBERT is not pre-trained with explicit cross-lingual supervision, transfer performance can further be …...

AbstractIn this paper we focus on connective identification and sense classification for explicit discourse relations in German, as two individual sub-tasks of the overarching Shallow Discourse Parsing task. We successively …...

AbstractThis work presents a method of word sense clustering that differentiates homonyms and merge homophones, taking Japanese as an example, where orthographical variation causes problem for language processing. It uses …...

AbstractContextualised embeddings such as BERT have become de facto state-of-the-art references in many NLP applications, thanks to their impressive performances. However, their opaqueness makes it hard to interpret their behaviour. …...