1 |
XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
MOLEMAN: Mention-Only Linking of Entities with a Mention Annotation Network ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
MOLEMAN: Mention-Only Linking of Entities with a Mention Annotation Network ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Asking without Telling: Exploring Latent Ontologies in Contextual Representations ...
|
|
|
|
Abstract:
The success of pretrained contextual encoders, such as ELMo and BERT, has brought a great deal of interest in what these models learn: do they, without explicit supervision, learn to encode meaningful notions of linguistic structure? If so, how is this structure encoded? To investigate this, we introduce latent subclass learning (LSL): a modification to existing classifier-based probing methods that induces a latent categorization (or ontology) of the probe's inputs. Without access to fine-grained gold labels, LSL extracts emergent structure from input representations in an interpretable and quantifiable form. In experiments, we find strong evidence of familiar categories, such as a notion of personhood in ELMo, as well as novel ontological distinctions, such as a preference for fine-grained semantic roles on core arguments. Our results provide unique new evidence of emergent structure in pretrained encoders, including departures from existing annotations which are inaccessible to earlier methods. ... : 21 pages, 8 figures, 11 tables. Published in EMNLP 2020 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; I.2.7
|
|
URL: https://arxiv.org/abs/2004.14513 https://dx.doi.org/10.48550/arxiv.2004.14513
|
|
BASE
|
|
Hide details
|
|
6 |
Cross-Lingual Morphological Tagging for Low-Resource Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|