DE eng

Search in the Catalogues and Directories

Hits 1 – 14 of 14

1
Probing for the Usage of Grammatical Number ...
BASE
Show details
2
On Homophony and Rényi Entropy ...
BASE
Show details
3
Finding Concept-specific Biases in Form--Meaning Associations ...
BASE
Show details
4
Quantifying Gender Bias Towards Politicians in Cross-Lingual Language Models ...
BASE
Show details
5
Revisiting the Uniform Information Density Hypothesis ...
BASE
Show details
6
How (Non-)Optimal is the Lexicon? ...
BASE
Show details
7
Disambiguatory Signals are Stronger in Word-initial Positions ...
BASE
Show details
8
SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection ...
BASE
Show details
9
Information-Theoretic Probing for Linguistic Structure ...
BASE
Show details
10
A Corpus for Large-Scale Phonetic Typology ...
BASE
Show details
11
Phonotactic Complexity and its Trade-offs ...
BASE
Show details
12
Predicting Declension Class from Form and Meaning ...
BASE
Show details
13
Pareto Probing: Trading Off Accuracy for Complexity ...
Abstract: The question of how to probe contextual word representations for linguistic structure in a way that is both principled and useful has seen significant attention recently in the NLP literature. In our contribution to this discussion, we argue for a probe metric that reflects the fundamental trade-off between probe complexity and performance: the Pareto hypervolume. To measure complexity, we present a number of parametric and non-parametric metrics. Our experiments using Pareto hypervolume as an evaluation metric show that probes often do not conform to our expectations---e.g., why should the non-contextual fastText representations encode more morpho-syntactic information than the contextual BERT representations? These results suggest that common, simplistic probing tasks, such as part-of-speech labeling and dependency arc labeling, are inadequate to evaluate the linguistic structure encoded in contextual word representations. This leads us to propose full dependency parsing as a probing task. In support of ... : Tiago Pimentel and Naomi Saphra contributed equally to this work. Camera ready version of EMNLP 2020 publication. Code available in https://github.com/rycolab/pareto-probing ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
URL: https://arxiv.org/abs/2010.02180
https://dx.doi.org/10.48550/arxiv.2010.02180
BASE
Hide details
14
A Tale of a Probe and a Parser ...
BASE
Show details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
14
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern