Yoav Goldberg

is this you? claim profile

∙ 0 followers
Bar-Ilan University ∙ Allen Institute for Artificial Intelligence

Senior Lecturer at Bar Ilan University's Computer Science Department, Post-Doc as a Research Scientist at Google Research New York, NLP Researcher at Google Inc. from 2011-2013, PhD Candidate / Teaching Assistant at Ben Gurion University from 2007-2011, Web and Crawling technologies at Picscout Inc. from 2004-2006, Networking / security / code / team leader at IDF from 1999-2004

Featured Co-authors

Masashi Sugiyama
182 publications
Graham Neubig
168 publications
Noah A. Smith
96 publications
Dan Roth
94 publications
Yejin Choi
90 publications
Chris Dyer
75 publications
Gang Niu
72 publications
Jonathan Berant
63 publications
Anders Søgaard
58 publications
Trevor Cohn
52 publications
Matt Gardner
45 publications

On the Power of Saturated Transformers: A View from Circuit Complexity

Transformers have become a standard architecture for many NLP problems. ...
06/30/2021 ∙ by William Merrill, et al. ∙ 0 ∙ share

read it
BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models

We show that with small-to-medium training data, fine-tuning only the bi...
06/18/2021 ∙ by Elad Ben Zaken, et al. ∙ 3 ∙ share

read it
Thinking Like Transformers

What is the computational model behind a Transformer? Where recurrent ne...
06/13/2021 ∙ by Gail Weiss, et al. ∙ 0 ∙ share

read it
Neural Extractive Search

Domain experts often need to extract structured information from large c...
06/08/2021 ∙ by Shauli Ravfogel, et al. ∙ 6 ∙ share

read it
Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction

When language models process syntactically complex sentences, do they us...
05/14/2021 ∙ by Shauli Ravfogel, et al. ∙ 24 ∙ share

read it
Provable Limitations of Acquiring Meaning from Ungrounded Form: What will Future Language Models Understand?

Language models trained on billions of tokens have recently led to unpre...
04/22/2021 ∙ by William Merrill, et al. ∙ 0 ∙ share

read it
Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes

We explore Few-Shot Learning (FSL) for Relation Classification (RC). Foc...
04/17/2021 ∙ by Ofer Sabo, et al. ∙ 0 ∙ share

read it
Back to Square One: Bias Detection, Training and Commonsense Disentanglement in the Winograd Schema

The Winograd Schema (WS) has been proposed as a test for measuring commo...
04/16/2021 ∙ by Yanai Elazar, et al. ∙ 0 ∙ share

read it
Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?

Large Transformers pretrained over clinical notes from Electronic Health...
04/15/2021 ∙ by Eric Lehman, et al. ∙ 0 ∙ share

read it
Contrastive Explanations for Model Interpretability

Contrastive explanations clarify why an event occurred in contrast to an...
03/02/2021 ∙ by Alon Jacovi, et al. ∙ 35 ∙ share

read it
Bootstrapping Relation Extractors using Syntactic Search by Examples

The advent of neural-networks in NLP brought with it substantial improve...
02/09/2021 ∙ by Matan Eyal, et al. ∙ 0 ∙ share

read it
A simple geometric proof for the benefit of depth in ReLU networks

We present a simple proof for the benefit of depth in multi-layer feedfo...
01/18/2021 ∙ by Asaf Amrami, et al. ∙ 0 ∙ share

read it
Facts2Story: Controlling Text Generation by Key Facts

Recent advancements in self-attention neural network architectures have ...
12/08/2020 ∙ by Eyal Orbach, et al. ∙ 0 ∙ share

read it
Parameter Norm Growth During Training of Transformers

The capacity of neural networks like the widely adopted transformer is k...
10/19/2020 ∙ by William Merrill, et al. ∙ 0 ∙ share

read it
It's not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT

Recent works have demonstrated that multilingual BERT (mBERT) learns ric...
10/16/2020 ∙ by Hila Gonen, et al. ∙ 10 ∙ share

read it
Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI

Trust is a central component of the interaction between people and AI, i...
10/15/2020 ∙ by Alon Jacovi, et al. ∙ 0 ∙ share

read it
The Extraordinary Failure of Complement Coercion Crowdsourcing

Crowdsourcing has eased and scaled up the collection of linguistic annot...
10/12/2020 ∙ by Yanai Elazar, et al. ∙ 3 ∙ share

read it
Unsupervised Distillation of Syntactic Information from Contextualized Word Representations

Contextualized word representations, such as ELMo and BERT, were shown t...
10/11/2020 ∙ by Shauli Ravfogel, et al. ∙ 6 ∙ share

read it
Relation Extraction as Two-way Span-Prediction

The current supervised relation classification (RC) task uses a single e...
10/09/2020 ∙ by Amir DN Cohen, et al. ∙ 0 ∙ share

read it
Exposing Shallow Heuristics of Relation Extraction Models with Challenge Data

The process of collecting and annotating training data may introduce dis...
10/07/2020 ∙ by Shachar Rosenman, et al. ∙ 0 ∙ share

read it
Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge

To what extent can a neural network systematically reason over symbolic ...
06/11/2020 ∙ by Alon Talmor, et al. ∙ 0 ∙ share

read it
Interactive Extractive Search over Biomedical Corpora

We present a system that allows life-science researchers to search a lin...
06/07/2020 ∙ by Hillel Taub-Tabib, et al. ∙ 0 ∙ share

read it
Syntactic Search by Example

We present a system that allows a user to search a large linguistically ...
06/04/2020 ∙ by Micah Shlain, et al. ∙ 0 ∙ share

read it
Aligning Faithful Interpretations with their Social Attribution

We find that the requirement of model interpretations to be faithful is ...
06/01/2020 ∙ by Alon Jacovi, et al. ∙ 6 ∙ share

read it
When Bert Forgets How To POS: Amnesic Probing of Linguistic Properties and MLM Predictions

A growing body of work makes use of probing in order to investigate the ...
06/01/2020 ∙ by Yanai Elazar, et al. ∙ 0 ∙ share

read it
Nakdan: Professional Hebrew Diacritizer

We present a system for automatic diacritization of Hebrew text. The sys...
05/07/2020 ∙ by Avi Shmidman, et al. ∙ 0 ∙ share

read it
pyBART: Evidence-based Syntactic Transformations for IE

Syntactic dependencies can be predicted with high accuracy, and are usef...
05/04/2020 ∙ by Aryeh Tiktinsky, et al. ∙ 0 ∙ share

read it
A Two-Stage Masked LM Method for Term Set Expansion

We tackle the task of Term Set Expansion (TSE): given a small seed set o...
05/03/2020 ∙ by Guy Kushilevitz, et al. ∙ 0 ∙ share

read it
A Formal Hierarchy of RNN Architectures

We develop a formal hierarchy of the expressive capacity of RNN architec...
04/18/2020 ∙ by William Merrill, et al. ∙ 0 ∙ share

read it
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection

The ability to control for the kinds of information encoded in neural re...
04/16/2020 ∙ by Shauli Ravfogel, et al. ∙ 0 ∙ share

read it
Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?

With the growing popularity of deep-learning based NLP models, comes a n...
04/07/2020 ∙ by Alon Jacovi, et al. ∙ 0 ∙ share

read it
Unsupervised Domain Clusters in Pretrained Language Models

The notion of "in-domain data" in NLP is often over-simplistic and vague...
04/05/2020 ∙ by Roee Aharoni, et al. ∙ 0 ∙ share

read it
Break It Down: A Question Understanding Benchmark

Understanding natural language questions entails the ability to break do...
01/31/2020 ∙ by Tomer Wolfson, et al. ∙ 0 ∙ share

read it
oLMpics – On what Language Model Pre-training Captures

Recent success of pre-trained language models (LMs) has spurred widespre...
12/31/2019 ∙ by Alon Talmor, et al. ∙ 14 ∙ share

read it
How does Grammatical Gender Affect Noun Representations in Gender-Marking Languages?

Many natural languages assign grammatical gender also to inanimate nouns...
10/30/2019 ∙ by Hila Gonen, et al. ∙ 0 ∙ share

read it
Learning Deterministic Weighted Automata with Queries and Counterexamples

We present an algorithm for extraction of a probabilistic deterministic ...
10/30/2019 ∙ by Gail Weiss, et al. ∙ 15 ∙ share

read it
Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning

We consider the situation in which a user has collected a small set of d...
10/29/2019 ∙ by Alon Jacovi, et al. ∙ 0 ∙ share

read it
Improving Quality and Efficiency in Plan-based Neural Data-to-Text Generation

We follow the step-by-step approach to neural data-to-text generation we...
09/22/2019 ∙ by Amit Moryossef, et al. ∙ 0 ∙ share

read it
Transfer Learning Between Related Tasks Using Expected Label Proportions

Deep learning systems thrive on abundance of labeled training data but s...
09/01/2019 ∙ by Matan Ben Noach, et al. ∙ 7 ∙ share

read it
Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets

Crowdsourcing has been the prevalent paradigm for creating natural langu...
08/21/2019 ∙ by Mor Geva, et al. ∙ 0 ∙ share

read it
Ab Antiquo: Proto-language Reconstruction with RNNs

Historical linguists have identified regularities in the process of hist...
08/07/2019 ∙ by Carlo Meloni, et al. ∙ 0 ∙ share

read it
Towards better substitution-based word sense induction

Word sense induction (WSI) is the task of unsupervised clustering of wor...
05/29/2019 ∙ by Asaf Amrami, et al. ∙ 0 ∙ share

read it
Where's My Head? Definition, Dataset and Models for Numeric Fused-Heads Identification and Resolution

We provide the first computational treatment of fused-heads construction...
05/26/2019 ∙ by Yanai Elazar, et al. ∙ 0 ∙ share

read it
Towards Neural Decompilation

We address the problem of automatic decompilation, converting a program ...
05/20/2019 ∙ by Omer Katz, et al. ∙ 0 ∙ share

read it
Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation

Data-to-text generation can be conceptually divided into two parts: orde...
04/06/2019 ∙ by Amit Moryossef, et al. ∙ 12 ∙ share

read it
Aligning Vector-spaces with Noisy Supervised Lexicons

The problem of learning to translate between two vector spaces given a s...
03/25/2019 ∙ by Noa Yehezkel Lubin, et al. ∙ 0 ∙ share

read it
Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages

How do typological properties such as word order and morphological case ...
03/15/2019 ∙ by Shauli Ravfogel, et al. ∙ 0 ∙ share

read it
Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them

Word embeddings are widely used in NLP for a vast range of tasks. It was...
03/09/2019 ∙ by Hila Gonen, et al. ∙ 0 ∙ share

read it
Filling Gender & Number Gaps in Neural Machine Translation with Black-box Context Injection

When translating from a language that does not morphologically mark info...
03/08/2019 ∙ by Amit Moryossef, et al. ∙ 0 ∙ share

read it
A Little Is Enough: Circumventing Defenses For Distributed Learning

Distributed learning is central for large-scale training of deep-learnin...
02/16/2019 ∙ by Moran Baruch, et al. ∙ 6 ∙ share

read it