565 citations · 2.5k across the 94 of their papers we have counts for
15 papers · 1 filter
Memory-Augmented Recurrent Neural Networks Can Learn Generalized Dyck Languages
Mirac Suzgun, Sebastian Gehrmann, Yonatan Belinkov +1
We introduce three memory-augmented Recurrent Neural Networks (MARNNs) and explore their capabilities on a series of simple language modeling tasks whose solutions require stack-ba…
On the Linguistic Representational Power of Neural Machine Translation Models
Yonatan Belinkov, Nadir Durrani, Fahim Dalvi +2
Despite the recent success of deep neural networks in natural language processing (NLP), their interpretability remains a challenge. We analyze the representations learned by neura…
A Constructive Prediction of the Generalization Error Across Scales
Jonathan S. Rosenfeld, Amir Rosenfeld, Yonatan Belinkov +1
The dependency of the generalization error of neural networks on model and dataset size is of critical importance both in practice and for understanding the theory of neural networ…
End-to-End Bias Mitigation by Modelling Biases in Corpora
Rabeeh Karimi Mahabadi, Yonatan Belinkov, James Henderson
Several recent studies have shown that strong natural language understanding (NLU) models are prone to relying on unwanted dataset biases without learning the underlying task, resu…
On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference
Yonatan Belinkov, Adam Poliak, Stuart M. Shieber +2
Popular Natural Language Inference (NLI) datasets have been shown to be tainted by hypothesis-only biases. Adversarial learning may help models ignore sensitive biases and spurious…
Don't Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference
Yonatan Belinkov, Adam Poliak, Stuart M. Shieber +2
Natural Language Inference (NLI) datasets often contain hypothesis-only biases---artifacts that allow models to achieve non-trivial performance without learning whether a premise e…
Findings of the First Shared Task on Machine Translation Robustness
Xian Li, Paul Michel, Antonios Anastasopoulos +7
We share the findings of the first shared task on improving robustness of Machine Translation (MT). The task provides a testbed representing challenges facing MT models deployed in…
Analyzing Phonetic and Graphemic Representations in End-to-End Automatic Speech Recognition
Yonatan Belinkov, Ahmed Ali, James Glass
End-to-end neural network systems for automatic speech recognition (ASR) are trained from acoustic features to text transcriptions. In contrast to modular ASR systems, which contai…
Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects
Gabriel Grand, Yonatan Belinkov
Visual question answering (VQA) models have been shown to over-rely on linguistic biases in VQA datasets, answering questions "blindly" without considering visual context. Adversar…
Analyzing the Structure of Attention in a Transformer Language Model
Jesse Vig, Yonatan Belinkov
The Transformer is a fully attention-based alternative to recurrent networks that has achieved state-of-the-art results across a range of NLP tasks. In this paper, we analyze the s…
LSTM Networks Can Perform Dynamic Counting
Mirac Suzgun, Sebastian Gehrmann, Yonatan Belinkov +1
In this paper, we systematically assess the ability of standard recurrent networks to perform dynamic counting and to encode hierarchical representations. All the neural models in…
Improving Neural Language Models by Segmenting, Attending, and Predicting the Future
Hongyin Luo, Lan Jiang, Yonatan Belinkov +1
Common language models typically predict the next word given the context. In this work, we propose a method that improves language modeling by learning to align the given context a…
Linguistic Knowledge and Transferability of Contextual Representations
Nelson F. Liu, Matt Gardner, Yonatan Belinkov +2
Contextual word representations derived from large-scale neural language models are successful across a diverse set of NLP tasks, suggesting that they encode useful and transferabl…
Character-based Surprisal as a Model of Reading Difficulty in the Presence of Error
Michael Hahn, Frank Keller, Yonatan Bisk +1
Intuitively, human readers cope easily with errors in text; typos, misspelling, word substitutions, etc. do not unduly disrupt natural reading. Previous work indicates that letter…
Analysis Methods in Neural Language Processing: A Survey
Yonatan Belinkov, James Glass
The field of natural language processing has seen impressive progress in recent years, with neural network models replacing many of the traditional systems. A plethora of new model…