paper-with-me

홈 › Papers

A Structural Probe for Finding Syntax in Word Representations

2019-06-01 · NAACL 2019 6 · John Hewitt, Christopher D. Manning

Recent work has improved our ability to detect linguistic knowledge in word representations. However, current methods for detecting syntactic knowledge do not test whether syntax trees are represented in their entirety. In this work, we propose a structural probe, which evaluates whether syntax trees are embedded in a linear transformation of a neural network{'}s word representation space. The probe identifies a linear transformation under which squared L2 distance encodes the distance between words in the parse tree, and one in which squared L2 norm encodes depth in the parse tree. Using our probe, we show that such transformations exist for both ELMo and BERT but not in baselines, providing evidence that entire syntax trees are embedded implicitly in deep models{'} vector geometry.

📄 PDF Abstract BibTeX

Code (1)

john-hewitt/structural-probes 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
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 &…

Similar Papers 제목 키워드 기반

Probing Syntax in Large Language Models: Successes and Remaining Challenges

2025-08-05 · Pablo J. Diego-Simón, Emmanuel Chemla, Jean-Rémi King, Yair Lakretz arxiv

The syntactic structures of sentences can be readily read-out from the activations of large language models (LLMs). However, the ``structural probes'' that have been developed to reveal this phenomenon are typically eval…

A polar coordinate system represents syntax in large language models

2024-12-07 · Pablo Diego-Simón, Stéphane d'Ascoli, Emmanuel Chemla, Yair Lakretz 외

Originally formalized with symbolic representations, syntactic trees may also be effectively represented in the activations of large language models (LLMs). Indeed, a 'Structural Probe' can find a subspace of neural acti…

Word Embeddings

Probing BERT in Hyperbolic Spaces

2021-04-08 · ICLR 2021 1 · Boli Chen, Yao Fu, Guangwei Xu, Pengjun Xie 외

Recently, a variety of probing tasks are proposed to discover linguistic properties learned in contextualized word embeddings. Many of these works implicitly assume these embeddings lay in certain metric spaces, typicall…

Word Embeddings

When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes

2022-04-20 · NAACL 2022 7 · Mycal Tucker, Tiwalayo Eisape, Peng Qian, Roger Levy 외

Recent causal probing literature reveals when language models and syntactic probes use similar representations. Such techniques may yield "false negative" causality results: models may use representations of syntax, but …

Language ModelingLanguage Modelling

When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Recent causal probing literature reveals when language models and syntactic probes use similar representations. Such techniques may yield ``false negative'' causality results: models may use representations of syntax, bu…

Language ModelingLanguage Modelling