3 |
Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Differentiable Multi-Agent Actor-Critic for Multi-Step Radiology Report Summarization ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Graph Algorithms for Multiparallel Word Alignment
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing ; The 2021 Conference on Empirical Methods in Natural Language Processing ; https://hal.archives-ouvertes.fr/hal-03424044 ; The 2021 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Nov 2021, Punta Cana, Dominica ; https://2021.emnlp.org/ (2021)
|
|
BASE
|
|
Show details
|
|
11 |
Does He Wink or Does He Nod? A Challenging Benchmark for Evaluating Word Understanding of Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
ParCourE: A Parallel Corpus Explorer for a Massively Multilingual Corpus ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Wine is Not v i n. -- On the Compatibility of Tokenizations Across Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Locating Language-Specific Information in Contextualized Embeddings ...
|
|
|
|
Abstract:
Multilingual pretrained language models (MPLMs) exhibit multilinguality and are well suited for transfer across languages. Most MPLMs are trained in an unsupervised fashion and the relationship between their objective and multilinguality is unclear. More specifically, the question whether MPLM representations are language-agnostic or they simply interleave well with learned task prediction heads arises. In this work, we locate language-specific information in MPLMs and identify its dimensionality and the layers where this information occurs. We show that language-specific information is scattered across many dimensions, which can be projected into a linear subspace. Our study contributes to a better understanding of MPLM representations, going beyond treating them as unanalyzable blobs of information. ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2109.08040 https://dx.doi.org/10.48550/arxiv.2109.08040
|
|
BASE
|
|
Hide details
|
|
18 |
Measuring and Improving Consistency in Pretrained Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|