1 |
Combining Static and Contextualised Multilingual Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Do Multilingual Language Models Capture Differing Moral Norms? ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Czech image captioning, machine translation, sentiment analysis and summarization (Neural Monkey models)
|
|
|
|
BASE
|
|
Show details
|
|
4 |
On the Language Neutrality of Pre-trained Multilingual Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
How Language-Neutral is Multilingual BERT? ...
|
|
|
|
Abstract:
Multilingual BERT (mBERT) provides sentence representations for 104 languages, which are useful for many multi-lingual tasks. Previous work probed the cross-linguality of mBERT using zero-shot transfer learning on morphological and syntactic tasks. We instead focus on the semantic properties of mBERT. We show that mBERT representations can be split into a language-specific component and a language-neutral component, and that the language-neutral component is sufficiently general in terms of modeling semantics to allow high-accuracy word-alignment and sentence retrieval but is not yet good enough for the more difficult task of MT quality estimation. Our work presents interesting challenges which must be solved to build better language-neutral representations, particularly for tasks requiring linguistic transfer of semantics. ... : 6 pages, 3 figures ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/1911.03310 https://dx.doi.org/10.48550/arxiv.1911.03310
|
|
BASE
|
|
Hide details
|
|
6 |
Czech image captioning, machine translation, and sentiment analysis (Neural Monkey models)
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Neural Monkey: An Open-source Tool for Sequence Learning
|
|
|
|
In: Prague Bulletin of Mathematical Linguistics , Vol 107, Iss 1, Pp 5-17 (2017) (2017)
|
|
BASE
|
|
Show details
|
|
12 |
KER - Keyword Extractor
|
|
Libovický, Jindřich. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2016
|
|
BASE
|
|
Show details
|
|
|
|