Search Results for author:
Found 19 papers, 11 papers with code
Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summaries
To address this problem, we handle the task of conversation retrieval based on text summaries of the conversations.
Self-Supervised Dataset Distillation for Transfer Learning
To achieve this, we also introduce the MSE between representations of the inner model and the self-supervised target model on the original full dataset for outer optimization.
Drug Discovery with Dynamic Goal-aware Fragments
Additionally, the existing fragment-based generative models cannot update the fragment vocabulary with goal-aware fragments newly discovered during the generation.
Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks
Large Language Models (LLMs) have shown promising performance in knowledge-intensive reasoning tasks that require a compound understanding of knowledge.
DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models
To tackle such limitations of existing NAS methods, we propose a paradigm shift from NAS to a novel conditional Neural Architecture Generation (NAG) framework based on diffusion models, dubbed DiffusionNAG.
On Divergence Measures for Bayesian Pseudocoresets
Finally, we propose a novel Bayesian pseudocoreset algorithm based on minimizing forward KL divergence.
Self-Distillation for Further Pre-training of Transformers
Pre-training a large transformer model on a massive amount of unlabeled data and fine-tuning it on labeled datasets for diverse downstream tasks has proven to be a successful strategy, for a variety of vision and natural language processing tasks.
Scalable Set Encoding with Universal Mini-Batch Consistency and Unbiased Full Set Gradient Approximation
Recent work on mini-batch consistency (MBC) for set functions has brought attention to the need for sequentially processing and aggregating chunks of a partitioned set while guaranteeing the same output for all partitions.
Set-based Meta-Interpolation for Few-Task Meta-Learning
Recently, several task augmentation methods have been proposed to tackle this issue using domain-specific knowledge to design augmentation techniques to densify the meta-training task distribution.
Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning
Thanks to the gradients aligned between tasks by our method, the model becomes less vulnerable to negative transfer and catastrophic forgetting.
Task Conditioned Stochastic Subsampling
Deep Learning algorithms are designed to operate on huge volumes of high dimensional data such as images.
Learning to Perturb Word Embeddings for Out-of-distribution QA
QA models based on pretrained language mod-els have achieved remarkable performance on various benchmark datasets. However, QA models do not generalize well to unseen data that falls outside the training distribution, due to distributional shifts. Data augmentation (DA) techniques which drop/replace words have shown to be effective in regularizing the model from overfitting to the training data. Yet, they may adversely affect the QA tasks since they incur semantic changes that may lead to wrong answers for the QA task.
Self-supervised Text-to-SQL Learning with Header Alignment Training
Since we can leverage a large amount of unlabeled data without any human supervision to train a model and transfer the knowledge to target tasks, self-supervised learning is a de-facto component for the recent success of deep learning in various fields.
Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-Learning
Then, the learned model can be used for downstream few-shot classification tasks, where we obtain task-specific parameters by performing semi-supervised EM on the latent representations of the support and query set, and predict labels of the query set by computing aggregated posteriors.
Contrastive Learning with Adversarial Perturbations for Conditional Text Generation
In this work, we propose to mitigate the conditional text generation problem by contrasting positive pairs with negative pairs, such that the model is exposed to various valid or incorrect perturbations of the inputs, for improved generalization.
Set Based Stochastic Subsampling
Deep models are designed to operate on huge volumes of high dimensional data such as images.
Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs
We validate our Information Maximizing Hierarchical Conditional Variational AutoEncoder (Info-HCVAE) on several benchmark datasets by evaluating the performance of the QA model (BERT-base) using only the generated QA pairs (QA-based evaluation) or by using both the generated and human-labeled pairs (semi-supervised learning) for training, against state-of-the-art baseline models.
Ranked #1 on
Question Generation
on Natural Questions
g2pM: A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset
Conversion of Chinese graphemes to phonemes (G2P) is an essential component in Mandarin Chinese Text-To-Speech (TTS) systems.
Ranked #2 on
Polyphone disambiguation
on CPP
Domain-agnostic Question-Answering with Adversarial Training
Adapting models to new domain without finetuning is a challenging problem in deep learning.
