paper-with-me

Papers

Naturalistic Causal Probing for Morpho-Syntax

2022-05-14 · Afra Amini, Tiago Pimentel, Clara Meister, Ryan Cotterell

Probing has become a go-to methodology for interpreting and analyzing deep neural models in natural language processing. However, there is still a lack of understanding of the limitations and weaknesses of various types of probes. In this work, we suggest a strategy for input-level intervention on naturalistic sentences. Using our approach, we intervene on the morpho-syntactic features of a sentence, while keeping the rest of the sentence unchanged. Such an intervention allows us to causally probe pre-trained models. We apply our naturalistic causal probing framework to analyze the effects of grammatical gender and number on contextualized representations extracted from three pre-trained models in Spanish: the multilingual versions of BERT, RoBERTa, and GPT-2. Our experiments suggest that naturalistic interventions lead to stable estimates of the causal effects of various linguistic properties. Moreover, our experiments demonstrate the importance of naturalistic causal probing when analyzing pre-trained models.

📄 PDF Abstract BibTeX arXiv:2205.07043

Code (1)

rycolab/naturalistic-causal-probing 공식 구현 pytorch

Tasks

Sentence

Methods 이 논문이 사용한 방법론

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…
Weight Decay 설명 없음
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…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…
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 $x$…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Morph Call: Probing Morphosyntactic Content of Multilingual Transformers

2021-04-26 · NAACL (SIGTYP) 2021 6 · Vladislav Mikhailov, Oleg Serikov, Ekaterina Artemova

The outstanding performance of transformer-based language models on a great variety of NLP and NLU tasks has stimulated interest in exploring their inner workings. Recent research has focused primarily on higher-level an…

Common Sense ReasoningMORPHPOSPOS Tagging+2

Holmes: A Benchmark to Assess the Linguistic Competence of Language Models

2024-04-29 · Andreas Waldis, Yotam Perlitz, Leshem Choshen, Yufang Hou 외

We introduce Holmes, a new benchmark designed to assess language models (LMs) linguistic competence - their unconscious understanding of linguistic phenomena. Specifically, we use classifier-based probing to examine LMs'…

Part-Of-Speech Tagging

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

Vyākarana: A Colorless Green Benchmark for Syntactic Evaluation in Indic Languages

2021-03-01 · EMNLP (MRL) 2021 11 · Rajaswa Patil, Jasleen Dhillon, Siddhant Mahurkar, Saumitra Kulkarni 외

While there has been significant progress towards developing NLU resources for Indic languages, syntactic evaluation has been relatively less explored. Unlike English, Indic languages have rich morphosyntax, grammatical …

Depth EstimationDepth PredictionPOSPOS Tagging+2