Building a Large Annotated Corpus of… Building a Large Annotated Corpus of English: The Penn Treebank Generating Typed Dependency Parses from… Generating Typed Dependency Parses from Phrase Structure Parses Distributed Representations of Word… Distributed Representations of Words and Phrases and their Compositionality Assessing the Ability of LSTMs to Learn… Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies Automatic differentiation in… Automatic differentiation in PyTorch DyNet: The Dynamic Neural Network Toolkit DyNet: The Dynamic Neural Network Toolkit Dissecting Contextual Word Embeddings… Dissecting Contextual Word Embeddings: Architecture and Representation LSTMs Can Learn Syntax-Sensitive… LSTMs Can Learn Syntax-Sensitive Dependencies Well, But Modeling Structure Makes Them Better Modeling garden path effects without explici… Modeling garden path effects without explicit hierarchical syntax RNNs as psycholinguistic subjects: Syntactic… RNNs as psycholinguistic subjects: Syntactic state and grammatical dependency Why Self-Attention? A Targeted Evaluation of… Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architectures BERT: Pre-training of Deep Bidirectional… BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding Visualizing and Measuring the Geometry… Visualizing and Measuring the Geometry of BERT A Systematic Analysis of Morphological Content i… A Systematic Analysis of Morphological Content in BERT Models for Multiple Languages Information-Theoretic Probing for Linguistic… Information-Theoretic Probing for Linguistic Structure The neural architecture of language: Integrativ… The neural architecture of language: Integrative modeling converges on predictive processing Finding Universal Grammatical Relations i… Finding Universal Grammatical Relations in Multilingual BERT Assessing Phrasal Representation and… Assessing Phrasal Representation and Composition in Transformers Conditional probing: measuring usable… Conditional probing: measuring usable information beyond a baseline When Do You Need Billions of Words of… When Do You Need Billions of Words of Pretraining Data? Exploring the Role of BERT Token… Exploring the Role of BERT Token Representations to Explain Sentence Probing Results How much pretraining data do language models… How much pretraining data do language models need to learn syntax? Do Syntactic Probes Probe Syntax?… Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing Linguistic Interpretability of… Linguistic Interpretability of Transformer-based Language Models: a systematic review A Structural Probe for Finding Syntax in Word… A Structural Probe for Finding Syntax in Word Representations 過去の参考文献 中心の論文 この論文を引用する論文 古い 新しい ノードをクリックするとフォーカスを固定、空白をクリックすると本論文に戻ります。ホバーで一時的にプレビューできます。各ノードのページはタイトルから開けます。
