1 |
A Latent-Variable Model for Intrinsic Probing ...
|
|
|
|
Abstract:
The success of pre-trained contextualized representations has prompted researchers to analyze them for the presence of linguistic information. Indeed, it is natural to assume that these pre-trained representations do encode some level of linguistic knowledge as they have brought about large empirical improvements on a wide variety of NLP tasks, which suggests they are learning true linguistic generalization. In this work, we focus on intrinsic probing, an analysis technique where the goal is not only to identify whether a representation encodes a linguistic attribute, but also to pinpoint where this attribute is encoded. We propose a novel latent-variable formulation for constructing intrinsic probes and derive a tractable variational approximation to the log-likelihood. Our results show that our model is versatile and yields tighter mutual information estimates than two intrinsic probes previously proposed in the literature. Finally, we find empirical evidence that pre-trained representations develop a ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2201.08214 https://dx.doi.org/10.48550/arxiv.2201.08214
|
|
BASE
|
|
Hide details
|
|
2 |
Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Investigating Failures of Automatic Translation in the Case of Unambiguous Gender ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
On the Relationships Between the Grammatical Genders of Inanimate Nouns and Their Co-Occurring Adjectives and Verbs ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
On the Idiosyncrasies of the Mandarin Chinese Classifier System ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
XNLI: Evaluating Cross-lingual Sentence Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Verb Argument Structure Alternations in Word and Sentence Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
The RepEval 2017 Shared Task: Multi-Genre Natural Language Inference with Sentence Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|