Search Results for author:
Found 16 papers, 1 papers with code
Neural Abstractive Multi-Document Summarization: Hierarchical or Flat Structure?
With regards to WikiSum (CITATION) that empowers applicative explorations of Neural Multi-Document Summarization (MDS) to learn from large scale dataset, this study develops two hierarchical Transformers (HT) that describe both the cross-token and cross-document dependencies, at the same time allow extended length of input documents.
D&M: Enriching E-commerce Videos with Sound Effects by Key Moment Detection and SFX Matching
Previous studies about adding SFX to videos perform video to SFX matching at a holistic level, lacking the ability of adding SFX to a specific moment.
Training-free Subject-Enhanced Attention Guidance for Compositional Text-to-image Generation
Furthermore, we propose a novel metric GroundingScore to evaluate subject alignment thoroughly.
AutoPoster: A Highly Automatic and Content-aware Design System for Advertising Poster Generation
Meanwhile, to our knowledge, we propose the first poster generation dataset that includes visual attribute annotations for over 76k posters.
A Semi-Autoregressive Graph Generative Model for Dependency Graph Parsing
And the latter assumes these components to be independent so that they can be outputted in a one-shot manner.
Geometry Aligned Variational Transformer for Image-conditioned Layout Generation
First, self-attention mechanism is adopted to model the contextual relationship within layout elements, while cross-attention mechanism is used to fuse the visual information of conditional images.
Parallel Hierarchical Transformer with Attention Alignment for Abstractive Multi-Document Summarization
In comparison to single-document summarization, abstractive Multi-Document Summarization (MDS) brings challenges on the representation and coverage of its lengthy and linked sources.
More Interpretable Graph Similarity Computation via Maximum Common Subgraph Inference
Our critical insight into INFMCS is the strong correlation between similarity score and Maximum Common Subgraph (MCS).
Composition-aware Graphic Layout GAN for Visual-textual Presentation Designs
Through both quantitative and qualitative evaluations, we demonstrate that the proposed model can synthesize high-quality graphic layouts according to image compositions.
Boosting Image Outpainting with Semantic Layout Prediction
Secondly, another GAN model is trained to synthesize real images based on the extended semantic layouts.
Global-aware Beam Search for Neural Abstractive Summarization
A global scoring mechanism is then developed to regulate beam search to generate summaries in a near-global optimal fashion.
Integrated Node Encoder for Labelled Textual Networks
Voluminous works have been implemented to exploit content-enhanced network embedding models, with little focus on the labelled information of nodes.
A Novel Distributed Representation of News (DRNews) for Stock Market Predictions
In this study, a novel Distributed Representation of News (DRNews) model is developed and applied in deep learning-based stock market predictions.
News2vec: News Network Embedding with Subnode Information
With the development of NLP technologies, news can be automatically categorized and labeled according to a variety of characteristics, at the same time be represented as low dimensional embeddings.
THU-HCSI at SemEval-2019 Task 3: Hierarchical Ensemble Classification of Contextual Emotion in Conversation
In this paper, we describe our hierarchical ensemble system designed for the SemEval-2019 task3, EmoContext.
Feature Engineering and Ensemble Modeling for Paper Acceptance Rank Prediction
Measuring research impact and ranking academic achievement are important and challenging problems.
