Asking without Telling: Exploring Latent Ontologies in Contextual Representations

By Julian Michael, Jan A. Botha, Ian Tenney. 2020

46 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

Probing Classifiers: Promises, Shortcomings, and Advances (2021, background): “Taking an information-theoretic perspective on probing, Pimentel et al. (2020b) proposed to use control functions instead of control tasks in order to compare probes.”
DirectProbe: Studying Representations without Classifiers (2021, methodology): “Using these classiﬁers, criteria such as accuracy or model complexity are used to evaluate the representation quality for the task (e.g. Goodwin et al., 2020; Pimentel et al., 2020a; Michael et al., 2020).”
Probing Classifiers: Promises, Shortcomings, and Alternatives (2021, background): “In an (at present, isolated) effort to alleviate this limitation, Michael, Botha, and Tenney (2020) propose to learn latent clusters relevant for predicting a property z .”
Finding Universal Grammatical Relations in Multilingual BERT (2020, background): “In concurrent work, Michael et al. (2020) also extend probing methodology, extracting latent ontologies from contextual representations without direct supervision.”