paper-with-me

홈 › Papers

Probing BERT’s priors with serial reproduction chains

2021-11-16 · ACL ARR November 2021 11 · Anonymous

We can learn as much about language models from what they say as we learn from their performance on targeted benchmarks. Sampling is a promising bottom-up method for probing, but generating samples from successful models like BERT remains challenging. Taking inspiration from theories of iterated learning in cognitive science, we explore the use of serial reproduction chains to probe BERT's priors. Although the masked language modeling objective does not guarantee a consistent joint distribution, we observe that a unique and consistent estimator of the ground-truth joint distribution may be obtained by a GSN sampler, which randomly selects which word to mask and reconstruct on each step. We compare the lexical and syntactic statistics of sentences from the resulting prior distribution against those of the ground-truth corpus distribution and elicit a large empirical sample of naturalness judgments to investigate how, exactly, the model deviates from human speakers. Our findings suggest the need to move beyond top-down evaluation methods toward bottom-up probing to capture the full richness of what has been learned about language.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingMasked Language Modeling

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Weight Decay 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Probing BERT's priors with serial reproduction chains

2022-02-24 · Takateru Yamakoshi, Thomas L. Griffiths, Robert D. Hawkins

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…

Language ModellingMasked Language Modeling

Probing BERT’s priors with serial reproduction chains

2022-05-01 · Findings (ACL) 2022 5 · Takateru Yamakoshi, Thomas Griffiths, Robert Hawkins

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…

Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction

2024-02-06 · Sreejan Kumar, Raja Marjieh, Byron Zhang, Declan Campbell 외

Humans extract useful abstractions of the world from noisy sensory data. Serial reproduction allows us to study how people construe the world through a paradigm similar to the game of telephone, where one person observes…

Evaluating Models of Robust Word Recognition with Serial Reproduction

2021-01-24 · Stephan C. Meylan, Sathvik Nair, Thomas L. Griffiths

Spoken communication occurs in a "noisy channel" characterized by high levels of environmental noise, variability within and between speakers, and lexical and syntactic ambiguity. Given these properties of the received l…

How memory biases affect information transmission: A rational analysis of serial reproduction

2008-12-01 · NeurIPS 2008 12 · Jing Xu, Thomas L. Griffiths

Many human interactions involve pieces of information being passed from one person to another, raising the question of how this process of information transmission is affected by the capacities of the agents involved. In…