Search Results for author:
Found 25 papers, 8 papers with code
Type-dependent Prompt CycleQAG : Cycle Consistency for Multi-hop Question Generation
Multi-hop question generation (QG) is the process of generating answer related questions, which requires aggregating multiple pieces of information and reasoning from different parts of the texts.
Structured Language Generation Model for Robust Structure Prediction
Previous work in structured prediction (e. g. NER, information extraction) using single model make use of explicit dataset information, which helps boost in-distribution performance but is orthogonal to robust generalization in real-world situations.
Punctuation Restoration Improves Structure Understanding without Supervision
Unsupervised learning objectives like language modeling and de-noising constitute a significant part in producing pre-trained models that perform various downstream applications from natural language understanding to conversational tasks.
Topology-Informed Graph Transformer
Transformers have revolutionized performance in Natural Language Processing and Vision, paving the way for their integration with Graph Neural Networks (GNNs).
Ranked #1 on
Graph Regression
on ZINC-full
A Gated MLP Architecture for Learning Topological Dependencies in Spatio-Temporal Graphs
The Cy2Mixer is composed of three blocks based on MLPs: A message-passing block for encapsulating spatial information, a cycle message-passing block for enriching topological information through cyclic subgraphs, and a temporal block for capturing temporal properties.
Ranked #2 on
Traffic Prediction
on PeMS04
Model-Free Reconstruction of Capacity Degradation Trajectory of Lithium-Ion Batteries Using Early Cycle Data
The method involves predicting a few knots at specific retention levels using a deep learning-based model and interpolating them to reconstruct the trajectory.
Biomedical image analysis competitions: The state of current participation practice
Of these, 84% were based on standard architectures.
Adversarial Lagrangian Integrated Contrastive Embedding for Limited Size Datasets
First, the accuracy improvement and training convergence of the proposed pre-trained adversarial transfer are shown on various subsets of datasets with few samples.
Where is VALDO? VAscular Lesions Detection and segmentatiOn challenge at MICCAI 2021
This challenge aimed to promote the development of methods for automated detection and segmentation of small and sparse imaging markers of cerebral small vessel disease, namely enlarged perivascular spaces (EPVS) (Task 1), cerebral microbleeds (Task 2) and lacunes of presumed vascular origin (Task 3) while leveraging weak and noisy labels.
BLOOD: Bi-level Learning Framework for Out-of-distribution Generalization
In this paper, we propose a novel bi-level learning framework for OOD generalization, which can effectively remove multiple unknown types of biases without any prior bias information or separate re-training steps of a model.
Meta-Learned Invariant Risk Minimization
Our method is more robust to the data with spurious correlations and can provide an invariant optimal classifier even when data from each distribution are scarce.
Distributed Associative Memory Network with Association Reinforcing Loss
To address these problems, here we introduce a novel Distributed Associative Memory architecture (DAM) with Association Reinforcing Loss (ARL) function which enhances the relation reasoning performance of memory augmented neural network.
Attentively Embracing Noise for Robust Latent Representation in BERT
We propose using all encoded transformer tokens and further encode them using a novel attentive embracement layer and multi-head attention layer.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
Distributed Associative Memory Network with Memory Refreshing Loss
For this procedure, we replace a single external memory with a set of multiple smaller associative memory blocks and update these sub-memory blocks simultaneously and independently for the distributed representation of input data.
Effective Crowdsourcing of Multiple Tasks for Comprehensive Knowledge Extraction
Information extraction from unstructured texts plays a vital role in the field of natural language processing.
Emotional Video to Audio Transformation Using Deep Recurrent Neural Networks and a Neuro-Fuzzy System
In this study, we propose a novel hybrid deep neural network that uses an Adaptive Neuro-Fuzzy Inference System to predict a video's emotion from its visual features and a deep Long Short-Term Memory Recurrent Neural Network to generate its corresponding audio signals with similar emotional inkling.
Vocoder-free End-to-End Voice Conversion with Transformer Network
The additional pre/post processing such as MFB and vocoder is not essential to convert real human speech to others.
Stacked DeBERT: All Attention in Incomplete Data for Text Classification
This is due to the fact that current approaches are built for and trained with clean and complete data, and thus are not able to extract features that can adequately represent incomplete data.
Application of Genetic Algorithm for More Efficient Multi-Layer Thickness Optimization in Solar Cells
The commonplace method used in optimization simulations, such as for optimizing the optical spacer layers' thicknesses, is the parameter sweep.
Chat Discrimination for Intelligent Conversational Agents with a Hybrid CNN-LMTGRU Network
Recently, intelligent dialog systems and smart assistants have attracted the attention of many, and development of novel dialogue agents have become a research challenge.
Human Action Generation with Generative Adversarial Networks
Inspired by the recent advances in generative models, we introduce a human action generation model in order to generate a consecutive sequence of human motions to formulate novel actions.
Representing Compositionality based on Multiple Timescales Gated Recurrent Neural Networks with Adaptive Temporal Hierarchy for Character-Level Language Models
The proposed model incorporates a biologically inspired temporal hierarchy in the architecture for representing multiple compositions of language in order to handle longer sequences for the character-level language model.
Towards Abstraction from Extraction: Multiple Timescale Gated Recurrent Unit for Summarization
The results also show that the temporal hierarchies help improve the ability of seq2seq models to capture compositionalities better without the presence of highly complex architectural hierarchies.
Word2Vec is a special case of Kernel Correspondence Analysis and Kernels for Natural Language Processing
The memory-efficient CA is then applied to a word-vector representation task.
