Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing
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?
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes
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 ModellingWhen Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes
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 ModellingProbing Syntax in Large Language Models: Successes and Remaining Challenges
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
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 ClusteringTAGProbing for Incremental Parse States in Autoregressive Language Models
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