Publications by Tags
Capsule Networks, Convolutional Neural Networks, Counterfactual Detection, Dataset Curation, Exposure Bias, Information Retrieval, k-NN, Knowledge Distillation, Language Modeling, Meta-Embedding, Metric Learning, Multilingual Transformers, Neural Language Models, Neural Network Compression, Policy-Gradient Methods, Pruning, Quantization, Regularization, Reward Shaping, Supervised Learning, Tensor Decomposition, Text Generation, Textual Similarity Evaluation, Transformers, Weight SharingCapsule Networks

James O' Neill
arXiv preprint arXiv:1805.07242TLDR: This paper proposes to extend capsule networks to a siamese network for metric learning tasks.
Capsule Networks, Metric LearningConvolutional Neural Networks

James O' Neill, Greg V. Steeg, Aram Galstyan
Asian Conference in Machine LearningTLDR: This paper proposes a dynamic weight sharing technique that learns to tie weights during retraining (compression phase).
Convolutional Neural Networks, Neural Network Compression, Transformers, Weight SharingCounterfactual Detection

James O' Neill, Polina Rozenshtein, Ryuichi Kiryo, Motoko Kubota and Danushka Bollegala
Empirical Methods for Natural Language Processing (EMNLP)TLDR: This paper proposes a dynamic weight sharing technique that learns to tie weights during retraining (compression phase).
Counterfactual Detection, Dataset Curation, Information Retrieval, Multilingual TransformersDataset Curation

James O' Neill, Polina Rozenshtein, Ryuichi Kiryo, Motoko Kubota and Danushka Bollegala
Empirical Methods for Natural Language Processing (EMNLP)TLDR: This paper proposes a dynamic weight sharing technique that learns to tie weights during retraining (compression phase).
Counterfactual Detection, Dataset Curation, Information Retrieval, Multilingual TransformersExposure Bias

James O' Neill, Danushka Bollegala
arXiv preprint arXiv:2101.09313TLDR: We propose Nearest-Neighbor Replacement Sampling, a technique to mitigate exposure bias by replacing ground truth tokens with semantically similar tokens during training.
Exposure Bias, k-NN, Language Modeling
James O' Neill, Danushka Bollegala
arXiv preprint arXiv:1909.03622TLDR: We propose pretrained textual similarity models to issue rewards based on the semantic similarity of generated and ground truth sequences for an actor-critic sequence predictor.
Exposure Bias, Policy-Gradient Methods, Reward Shaping, Text GenerationInformation Retrieval

James O' Neill, Polina Rozenshtein, Ryuichi Kiryo, Motoko Kubota and Danushka Bollegala
Empirical Methods for Natural Language Processing (EMNLP)TLDR: This paper proposes a dynamic weight sharing technique that learns to tie weights during retraining (compression phase).
Counterfactual Detection, Dataset Curation, Information Retrieval, Multilingual TransformersKnowledge Distillation

James O' Neill
arXiv preprint arXiv:2006.03669TLDR: This paper provides a thorough overview of weight sharing, pruning, tensor decomposition, knowledge distillation and quantization.
Knowledge Distillation, Pruning, Quantization, Tensor Decomposition, Weight Sharing
James O' Neill, Danushka Bollegala
Asian Conference in Machine LearningTLDR: This paper proposes a dynamic weight sharing technique that learns to tie weights during retraining (compression phase).
Knowledge Distillation, Neural Network Compression
James O' Neill, Sourav Dutta, Haytham Assem
arXiv preprint arXiv:2109.15014TLDR: This paper proposes the combination of pruning and self-distillation and uses a cross-correlation based KD objective that naturally fits with magnitude-based pruning.
Knowledge Distillation, Neural Network Compression, PruningLanguage Modeling

James O' Neill, Danushka Bollegala
arXiv preprint arXiv:2101.09313TLDR: We propose Nearest-Neighbor Replacement Sampling, a technique to mitigate exposure bias by replacing ground truth tokens with semantically similar tokens during training.
Exposure Bias, k-NN, Language ModelingMeta-Embedding

James O' Neill, Danushka Bollegala
European Conference on Artificial IntelligenceTLDR: We propose supervised meta-embedding that learns to reconstruct an ensemble of static word embeddings while learning on a downstream task.
Meta-Embedding, Regularization, Supervised LearningMetric Learning

James O' Neill
arXiv preprint arXiv:1805.07242TLDR: This paper proposes to extend capsule networks to a siamese network for metric learning tasks.
Capsule Networks, Metric LearningMultilingual Transformers

James O' Neill, Polina Rozenshtein, Ryuichi Kiryo, Motoko Kubota and Danushka Bollegala
Empirical Methods for Natural Language Processing (EMNLP)TLDR: This paper proposes a dynamic weight sharing technique that learns to tie weights during retraining (compression phase).
Counterfactual Detection, Dataset Curation, Information Retrieval, Multilingual TransformersNeural Language Models

James O' Neill, Danushka Bollegala
Pacific Association of Computation Linguistics (PACLING)TLDR: We propose pretrained textual similarity models to evaluate neural language models.
Neural Language Models, Textual Similarity EvaluationNeural Network Compression

James O' Neill, Danushka Bollegala
Asian Conference in Machine LearningTLDR: This paper proposes a dynamic weight sharing technique that learns to tie weights during retraining (compression phase).
Knowledge Distillation, Neural Network Compression
James O' Neill, Sourav Dutta, Haytham Assem
arXiv preprint arXiv:2109.15014TLDR: This paper proposes the combination of pruning and self-distillation and uses a cross-correlation based KD objective that naturally fits with magnitude-based pruning.
Knowledge Distillation, Neural Network Compression, Pruning
James O' Neill, Greg V. Steeg, Aram Galstyan
Asian Conference in Machine LearningTLDR: This paper proposes a dynamic weight sharing technique that learns to tie weights during retraining (compression phase).
Convolutional Neural Networks, Neural Network Compression, Transformers, Weight SharingPolicy-Gradient Methods

James O' Neill, Danushka Bollegala
arXiv preprint arXiv:1909.03622TLDR: We propose pretrained textual similarity models to issue rewards based on the semantic similarity of generated and ground truth sequences for an actor-critic sequence predictor.
Exposure Bias, Policy-Gradient Methods, Reward Shaping, Text GenerationPruning

James O' Neill
arXiv preprint arXiv:2006.03669TLDR: This paper provides a thorough overview of weight sharing, pruning, tensor decomposition, knowledge distillation and quantization.
Knowledge Distillation, Pruning, Quantization, Tensor Decomposition, Weight Sharing
James O' Neill, Sourav Dutta, Haytham Assem
arXiv preprint arXiv:2109.15014TLDR: This paper proposes the combination of pruning and self-distillation and uses a cross-correlation based KD objective that naturally fits with magnitude-based pruning.
Knowledge Distillation, Neural Network Compression, PruningQuantization

James O' Neill
arXiv preprint arXiv:2006.03669TLDR: This paper provides a thorough overview of weight sharing, pruning, tensor decomposition, knowledge distillation and quantization.
Knowledge Distillation, Pruning, Quantization, Tensor Decomposition, Weight SharingRegularization

James O' Neill, Danushka Bollegala
European Conference on Artificial IntelligenceTLDR: We propose supervised meta-embedding that learns to reconstruct an ensemble of static word embeddings while learning on a downstream task.
Meta-Embedding, Regularization, Supervised LearningReward Shaping

James O' Neill, Danushka Bollegala
arXiv preprint arXiv:1909.03622TLDR: We propose pretrained textual similarity models to issue rewards based on the semantic similarity of generated and ground truth sequences for an actor-critic sequence predictor.
Exposure Bias, Policy-Gradient Methods, Reward Shaping, Text GenerationSupervised Learning

James O' Neill, Danushka Bollegala
European Conference on Artificial IntelligenceTLDR: We propose supervised meta-embedding that learns to reconstruct an ensemble of static word embeddings while learning on a downstream task.
Meta-Embedding, Regularization, Supervised LearningTensor Decomposition

James O' Neill
arXiv preprint arXiv:2006.03669TLDR: This paper provides a thorough overview of weight sharing, pruning, tensor decomposition, knowledge distillation and quantization.
Knowledge Distillation, Pruning, Quantization, Tensor Decomposition, Weight SharingText Generation

James O' Neill, Danushka Bollegala
arXiv preprint arXiv:1909.03622TLDR: We propose pretrained textual similarity models to issue rewards based on the semantic similarity of generated and ground truth sequences for an actor-critic sequence predictor.
Exposure Bias, Policy-Gradient Methods, Reward Shaping, Text GenerationTextual Similarity Evaluation

James O' Neill, Danushka Bollegala
Pacific Association of Computation Linguistics (PACLING)TLDR: We propose pretrained textual similarity models to evaluate neural language models.
Neural Language Models, Textual Similarity EvaluationTransformers

James O' Neill, Greg V. Steeg, Aram Galstyan
Asian Conference in Machine LearningTLDR: This paper proposes a dynamic weight sharing technique that learns to tie weights during retraining (compression phase).
Convolutional Neural Networks, Neural Network Compression, Transformers, Weight SharingWeight Sharing

James O' Neill
arXiv preprint arXiv:2006.03669TLDR: This paper provides a thorough overview of weight sharing, pruning, tensor decomposition, knowledge distillation and quantization.
Knowledge Distillation, Pruning, Quantization, Tensor Decomposition, Weight Sharing
James O' Neill, Greg V. Steeg, Aram Galstyan
Asian Conference in Machine LearningTLDR: This paper proposes a dynamic weight sharing technique that learns to tie weights during retraining (compression phase).
Convolutional Neural Networks, Neural Network Compression, Transformers, Weight Sharingk-NN

James O' Neill, Danushka Bollegala
arXiv preprint arXiv:2101.09313TLDR: We propose Nearest-Neighbor Replacement Sampling, a technique to mitigate exposure bias by replacing ground truth tokens with semantically similar tokens during training.
Exposure Bias, k-NN, Language Modeling