Lune

ACL Findings2022

Probing BERT's priors with serial reproduction chains

Takateru Yamakoshi, Thomas L. Griffiths, Robert D. Hawkins

Abstract

Sampling is a promising bottom-up method for exposing what generative models have learned about language, but it remains unclear how to generate representative samples from popular masked language models (MLMs) like BERT. The MLM objective yields a dependency network with no guarantee of consistent conditional distributions, posing a problem for naive approaches. Drawing from theories of iterated learning in cognitive science, we explore the use of serial reproduction chains to sample from BERT's priors. In particular, we observe that a unique and consistent estimator of the ground-truth joint distribution is given by a Generative Stochastic Network (GSN) sampler, which randomly selects which token to mask and reconstruct on each step. We show that the lexical and syntactic statistics of sentences from GSN chains closely match the ground-truth corpus distribution and perform better than other methods in a large corpus of naturalness judgments. Our findings establish a firmer theoretical foundation for bottom-up probing and highlight richer deviations from human priors 1 .

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

3 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers cites Language GANs Falling Short
  • MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers cites Language Models are Few-Shot Learners
  • MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers cites The Curious Case of Neural Text Degeneration
  • Language Models are Few-Shot Learners cites The Curious Case of Neural Text Degeneration
  • Amortizing intractable inference in large language models cites The Curious Case of Neural Text Degeneration
  • The Curious Case of Neural Text Degeneration cites Language GANs Falling Short
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers3

  1. Amortizing intractable inference in large language modelsEdward J. Hu, Moksh Jain, Eric Elmoznino, Younesse Kaddar et al.ICLR 2024 · 91 citations
  2. QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine TranslationGonçalo Rui Alves Faria, Sweta Agrawal, António Farinhas, Ricardo Rei et al.NeurIPS 2024 · 23 citations
  3. Quantifying Human Priors over Social and Navigation NetworksGecia Bravo HermsdorffICML 2023 · 1 citation

Builds on14

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. The Curious Case of Neural Text DegenerationAri Holtzman, Jan Buys, Li Du, Maxwell Forbes et al.ICLR 2020 · 4,112 citations
  3. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
  4. MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence FrontiersKrishna Pillutla, Swabha Swayamdipta, Rowan Zellers, John Thickstun et al.NeurIPS 2021 · 606 citations
  5. Language GANs Falling ShortMassimo Caccia, Lucas Caccia, William Fedus, Hugo Larochelle et al.ICLR 2020 · 236 citations

Related papers

  1. Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word OrderYi Liao, Xin Jiang, Qun LiuACL 2020 · 28 citations
  2. Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis--HastingsKartik Goyal, Chris Dyer, Taylor Berg-KirkpatrickICLR 2022 · 53 citations
  3. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than GeneratorsKevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. ManningICLR 2020 · 541 citations
  4. From BERT's Point of View: Revealing the Prevailing Contextual DifferencesCarolin Schuster, Simon HegelichACL Findings 2022 · 4 citations
  5. What if This Modified That? Syntactic Interventions with Counterfactual EmbeddingsMycal Tucker, Peng Qian, Roger LevyACL Findings 2021 · 16 citations
Dusk over the sea between two cliffs drawn in fine vertical lines