What do you learn from context? Probing for sentence structure in contextualized word representations

by   Ian Tenney, et al.

Contextualized representation models such as ELMo (Peters et al., 2018a) and BERT (Devlin et al., 2018) have recently achieved state-of-the-art results on a diverse array of downstream NLP tasks. Building on recent token-level probing work, we introduce a novel edge probing task design and construct a broad suite of sub-sentence tasks derived from the traditional structured NLP pipeline. We probe word-level contextual representations from four recent models and investigate how they encode sentence structure across a range of syntactic, semantic, local, and long-range phenomena. We find that existing models trained on language modeling and translation produce strong representations for syntactic phenomena, but only offer comparably small improvements on semantic tasks over a non-contextual baseline.


page 1

page 2

page 3

page 4


FlauBERT: Unsupervised Language Model Pre-training for French

Language models have become a key step to achieve state-of-the-art resul...

Context is Key: Grammatical Error Detection with Contextual Word Representations

Grammatical error detection (GED) in non-native writing requires systems...

Grammatical Analysis of Pretrained Sentence Encoders with Acceptability Judgments

Recent pretrained sentence encoders achieve state of the art results on ...

BERT has a Moral Compass: Improvements of ethical and moral values of machines

Allowing machines to choose whether to kill humans would be devastating ...

Encouraging Paragraph Embeddings to Remember Sentence Identity Improves Classification

While paragraph embedding models are remarkably effective for downstream...

A Non-Linear Structural Probe

Probes are models devised to investigate the encoding of knowledge – e.g...

Learning for Expressive Task-Related Sentence Representations

NLP models learn sentence representations for downstream tasks by tuning...

Please sign up or login with your details

Forgot password? Click here to reset