Search Results for author:
Found 18 papers, 10 papers with code
It’s not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT
Recent works have demonstrated that multilingual BERT (mBERT) learns rich cross-lingual representations, that allow for transfer across languages.
Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions
Our causal framework and our results demonstrate the importance of studying datasets and the benefits of causality for understanding NLP models.
Analyzing Gender Representation in Multilingual Models
Multilingual language models were shown to allow for nontrivial transfer across scripts and languages.
Linear Adversarial Concept Erasure
Modern neural models trained on textual data rely on pre-trained representations that emerge without direct supervision.
Adversarial Concept Erasure in Kernel Space
The representation space of neural models for textual data emerges in an unsupervised manner during training.
BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models
We introduce BitFit, a sparse-finetuning method where only the bias-terms of the model (or a subset of them) are being modified.
Neural Extractive Search
We advocate for a search paradigm called ``extractive search'', in which a search query is enriched with capture-slots, to allow for such rapid extraction.
Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction
We apply this method to study how BERT models of different sizes process relative clauses (RCs).
Contrastive Explanations for Model Interpretability
Our method is based on projecting model representation to a latent space that captures only the features that are useful (to the model) to differentiate two potential decisions.
Measuring and Improving Consistency in Pretrained Language Models
In this paper we study the question: Are Pretrained Language Models (PLMs) consistent with respect to factual knowledge?
It's not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT
Recent works have demonstrated that multilingual BERT (mBERT) learns rich cross-lingual representations, that allow for transfer across languages.
The Extraordinary Failure of Complement Coercion Crowdsourcing
In this work, we follow known methodologies of collecting labeled data for the complement coercion phenomenon.
Unsupervised Distillation of Syntactic Information from Contextualized Word Representations
Contextualized word representations, such as ELMo and BERT, were shown to perform well on various semantic and syntactic tasks.
Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals
In this work, we point out the inability to infer behavioral conclusions from probing results and offer an alternative method that focuses on how the information is being used, rather than on what information is encoded.
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection
The ability to control for the kinds of information encoded in neural representation has a variety of use cases, especially in light of the challenge of interpreting these models.
Ab Antiquo: Neural Proto-language Reconstruction
Historical linguists have identified regularities in the process of historic sound change.
Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages
How do typological properties such as word order and morphological case marking affect the ability of neural sequence models to acquire the syntax of a language?
Can LSTM Learn to Capture Agreement? The Case of Basque
We propose the Basque agreement prediction task as challenging benchmark for models that attempt to learn regularities in human language.
