conftrace_

probing analysis

59 papers

Explore in graph

Co-occurring keywords

representation learning (6206) language model (4599) large language model (13587) pre-trained language model (1515) pretrained language model (1030) natural language inference (1287) linguistic knowledge (77) model interpretability (519) multilingual model (925) transformer model (1996)

Papers

Post-hoc analysis of Arabic transformer models EMNLP 2022
Analyzing the Mono- and Cross-Lingual Pretraining Dynamics of Multilingual Language Models EMNLP 2022
Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens NAACL 2022
Measuring Context-Word Biases in Lexical Semantic Datasets EMNLP 2022
How Distributed are Distributed Representations? An Observation on the Locality of Syntactic Information in Verb Agreement Tasks ACL 2022
Probing for the Usage of Grammatical Number ACL 2022
Probing speech emotion recognition transformers for linguistic knowledge INTERSPEECH 2022
On the Importance of Data Size in Probing Fine-tuned Models ACL 2022
On the Role of Pre-trained Language Models in Word Ordering: A Case Study with BART COLING 2022
Exploring the Effects of Negation and Grammatical Tense on Bias Probes AACL 2022
Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction EMNLP 2021
Finding BERT’s Idiomatic Key IJCNLP 2021
When Do You Need Billions of Words of Pretraining Data? IJCNLP 2021
What BERTs and GPTs know about your brand? Probing contextual language models for affect associations NAACL 2021
DirectProbe: Studying Representations without Classifiers NAACL 2021
Syntactic Perturbations Reveal Representational Correlates of Hierarchical Phrase Structure in Pretrained Language Models ACL 2021
Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers NAACL 2021
Do Language Models Know the Way to Rome? EMNLP 2021
Probing Across Time: What Does RoBERTa Know and When? EMNLP 2021
To what extent do human explanations of model behavior align with actual model behavior? EMNLP 2021
Investigating Negation in Pre-trained Vision-and-language Models EMNLP 2021
Who’s on First?: Probing the Learning and Representation Capabilities of Language Models on Deterministic Closed Domains EMNLP 2021
How does BERT’s attention change when you fine-tune? An analysis methodology and a case study in negation scope ACL 2020
Classifier Probes May Just Learn from Linear Context Features COLING 2020
Probing Neural Dialog Models for Conversational Understanding ACL 2020