
-
Probing Classifiers: Promises, Shortcomings, and Alternatives
Probing classifiers have emerged as one of the prominent methodologies f...
read it
-
Learning from others' mistakes: Avoiding dataset biases without modeling them
State-of-the-art natural language processing (NLP) models often learn to...
read it
-
Similarity Analysis of Self-Supervised Speech Representations
Self-supervised speech representation learning has recently been a prosp...
read it
-
Analyzing Individual Neurons in Pre-trained Language Models
While a lot of analysis has been carried to demonstrate linguistic knowl...
read it
-
Probing Neural Dialog Models for Conversational Understanding
The predominant approach to open-domain dialog generation relies on end-...
read it
-
The Sensitivity of Language Models and Humans to Winograd Schema Perturbations
Large-scale pretrained language models are the major driving force behin...
read it
-
Similarity Analysis of Contextual Word Representation Models
This paper investigates contextual word representation models from the l...
read it
-
Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias
Common methods for interpreting neural models in natural language proces...
read it
-
Exploiting Redundancy in Pre-trained Language Models for Efficient Transfer Learning
Large pre-trained contextual word representations have transformed the f...
read it
-
Memory-Augmented Recurrent Neural Networks Can Learn Generalized Dyck Languages
We introduce three memory-augmented Recurrent Neural Networks (MARNNs) a...
read it
-
On the Linguistic Representational Power of Neural Machine Translation Models
Despite the recent success of deep neural networks in natural language p...
read it
-
A Constructive Prediction of the Generalization Error Across Scales
The dependency of the generalization error of neural networks on model a...
read it
-
On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference
Popular Natural Language Inference (NLI) datasets have been shown to be ...
read it
-
Don't Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference
Natural Language Inference (NLI) datasets often contain hypothesis-only ...
read it
-
Analyzing Phonetic and Graphemic Representations in End-to-End Automatic Speech Recognition
End-to-end neural network systems for automatic speech recognition (ASR)...
read it
-
Findings of the First Shared Task on Machine Translation Robustness
We share the findings of the first shared task on improving robustness o...
read it
-
Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects
Visual question answering (VQA) models have been shown to over-rely on l...
read it
-
LSTM Networks Can Perform Dynamic Counting
In this paper, we systematically assess the ability of standard recurren...
read it
-
Analyzing the Structure of Attention in a Transformer Language Model
The Transformer is a fully attention-based alternative to recurrent netw...
read it
-
Improving Neural Language Models by Segmenting, Attending, and Predicting the Future
Common language models typically predict the next word given the context...
read it
-
Linguistic Knowledge and Transferability of Contextual Representations
Contextual word representations derived from large-scale neural language...
read it
-
Character-based Surprisal as a Model of Human Reading in the Presence of Errors
Intuitively, human readers cope easily with errors in text; typos, missp...
read it
-
NeuroX: A Toolkit for Analyzing Individual Neurons in Neural Networks
We present a toolkit to facilitate the interpretation and understanding ...
read it
-
What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models
Despite the remarkable evolution of deep neural networks in natural lang...
read it
-
Analysis Methods in Neural Language Processing: A Survey
The field of natural language processing has seen impressive progress in...
read it
-
Identifying and Controlling Important Neurons in Neural Machine Translation
Neural machine translation (NMT) models learn representations containing...
read it
-
On Evaluating the Generalization of LSTM Models in Formal Languages
Recurrent Neural Networks (RNNs) are theoretically Turing-complete and e...
read it
-
Studying the History of the Arabic Language: Language Technology and a Large-Scale Historical Corpus
Arabic is a widely-spoken language with a long and rich history, but exi...
read it
-
On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference
We propose a process for investigating the extent to which sentence repr...
read it
-
Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks
While neural machine translation (NMT) models provide improved translati...
read it
-
Synthetic and Natural Noise Both Break Neural Machine Translation
Character-based neural machine translation (NMT) models alleviate out-of...
read it
-
Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems
Neural models have become ubiquitous in automatic speech recognition sys...
read it
-
Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging
Word segmentation plays a pivotal role in improving any Arabic NLP appli...
read it
-
Neural Machine Translation Training in a Multi-Domain Scenario
In this paper, we explore alternative ways to train a neural machine tra...
read it
-
What do Neural Machine Translation Models Learn about Morphology?
Neural machine translation (MT) models obtain state-of-the-art performan...
read it
-
Shamela: A Large-Scale Historical Arabic Corpus
Arabic is a widely-spoken language with a rich and long history spanning...
read it
-
Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
There is a lot of research interest in encoding variable length sentence...
read it