Search Results for author:
Found 14 papers, 4 papers with code
Entity Attribute Relation Extraction with Attribute-Aware Embeddings
Entity-attribute relations are a fundamental component for building large-scale knowledge bases, which are widely employed in modern search engines.
Multi-Frame Self-Supervised Depth Estimation with Multi-Scale Feature Fusion in Dynamic Scenes
However, the spatial-temporal feature leads to accuracy degradation in dynamic scenes.
KRLS: Improving End-to-End Response Generation in Task Oriented Dialog with Reinforced Keywords Learning
In task-oriented dialogs, an informative and successful system response needs to include key information such as the phone number of a hotel.
Improving Model Training via Self-learned Label Representations
In this work, we demonstrate that more sophisticated label representations are better for classification than the usual one-hot encoding.
Diverse Title Generation for Stack Overflow Posts with Multiple Sampling Enhanced Transformer
Stack Overflow is one of the most popular programming communities where developers can seek help for their encountered problems.
A recipe of training neural network-based LDPC decoders
It is known belief propagation decoding variants of LDPC codes can be unrolled easily as neural networks after assigning differed weights to message passing edges flexibly.
FastKASSIM: A Fast Tree Kernel-Based Syntactic Similarity Metric
Syntax is a fundamental component of language, yet few metrics have been employed to capture syntactic similarity or coherence at the utterance- and document-level.
Improving Stack Overflow question title generation with copying enhanced CodeBERT model and bi-modal information
However, only using the code snippets in the question body cannot provide sufficient information for title generation, and LSTMs cannot capture the long-range dependencies between tokens.
Asymptotic spreading of KPP reactive fronts in heterogeneous shifting environments
We study the asymptotic spreading of Kolmogorov-Petrovsky-Piskunov (KPP) fronts in heterogeneous shifting habitats, with any number of shifting speeds, by further developing the method based on the theory of viscosity solutions of Hamilton-Jacobi equations.
Analysis of PDEs 35B40, 35K57, 35R10, 35D40
SIGL: Securing Software Installations Through Deep Graph Learning
We introduce SIGL, a new tool for detecting malicious behavior during software installation.
Heterogeneous Graph Matching Networks
Information systems have widely been the target of malware attacks.
Adaptive Transfer Learning of Multi-View Time Series Classification
In this paper, we first proposed a general adaptive transfer learning framework for multi-view time series data, which shows strong ability in storing inter-view importance value in the process of knowledge transfer.
Adversarial Defense Framework for Graph Neural Network
How to address the vulnerabilities and defense GNN against the adversarial attacks?
Learning to Generate Posters of Scientific Papers by Probabilistic Graphical Models
In order to bridge the gap between panel attributes and the composition within each panel, we also propose a recursive page splitting algorithm to generate the panel layout for a poster.
