paper-with-me

Papers

Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing

2021-06-04 · NAACL 2021 4 · Rowan Hall Maudslay, Ryan Cotterell

Analysing whether neural language models encode linguistic information has become popular in NLP. One method of doing so, which is frequently cited to support the claim that models like BERT encode syntax, is called probing; probes are small supervised models trained to extract linguistic information from another model's output. If a probe is able to predict a particular structure, it is argued that the model whose output it is trained on must have implicitly learnt to encode it. However, drawing a generalisation about a model's linguistic knowledge about a specific phenomena based on what a probe is able to learn may be problematic: in this work, we show that semantic cues in training data means that syntactic probes do not properly isolate syntax. We generate a new corpus of semantically nonsensical but syntactically well-formed Jabberwocky sentences, which we use to evaluate two probes trained on normal data. We train the probes on several popular language models (BERT, GPT, and RoBERTa), and find that in all settings they perform worse when evaluated on these data, for one probe by an average of 15.4 UUAS points absolute. Although in most cases they still outperform the baselines, their lead is reduced substantially, e.g. by 53% in the case of BERT for one probe. This begs the question: what empirical scores constitute knowing syntax?

📄 PDF Abstract BibTeX arXiv:2106.02559

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

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 &…
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
Adam 설명 없음
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.
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

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

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…

Deep Clustering of Text Representations for Supervision-free Probing of Syntax

2020-10-24 · Vikram Gupta, Haoyue Shi, Kevin Gimpel, Mrinmaya Sachan

We explore deep clustering of text representations for unsupervised model interpretation and induction of syntax. As these representations are high-dimensional, out-of-the-box methods like KMeans do not work well. Thus, …

ClusteringDeep ClusteringTAG

Probing for Incremental Parse States in Autoregressive Language Models

2022-11-17 · Tiwalayo Eisape, Vineet Gangireddy, Roger P. Levy, Yoon Kim

Next-word predictions from autoregressive neural language models show remarkable sensitivity to syntax. This work evaluates the extent to which this behavior arises as a result of a learned ability to maintain implicit r…

SensitivitySentence