T
Trung Bui
Researcher at Adobe Systems
Publications - 100
Citations - 2241
Trung Bui is an academic researcher from Adobe Systems. The author has contributed to research in topics: Image editing & Computer science. The author has an hindex of 21, co-authored 99 publications receiving 1561 citations. Previous affiliations of Trung Bui include École Polytechnique Fédérale de Lausanne & University of Twente.
Papers
More filters
Posted Content
A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents
Arman Cohan,Franck Dernoncourt,Doo Soon Kim,Trung Bui,Seokhwan Kim,Walter Chang,Nazli Goharian +6 more
TL;DR: This work proposes the first model for abstractive summarization of single, longer-form documents (e.g., research papers), consisting of a new hierarchical encoder that models the discourse structure of a document, and an attentive discourse-aware decoder to generate the summary.
Proceedings ArticleDOI
A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents
Arman Cohan,Franck Dernoncourt,Doo Soon Kim,Trung Bui,Seokhwan Kim,Walter Chang,Nazli Goharian +6 more
TL;DR: The authors propose a hierarchical encoder that models the discourse structure of a document and an attentive discourse-aware decoder to generate the summary, which significantly outperforms state-of-the-art models.
Proceedings ArticleDOI
Visual to Sound: Generating Natural Sound for Videos in the Wild
TL;DR: In this article, the task of generating sound given visual input is addressed and a learning-based method is applied to generate raw waveform samples given input video frames and evaluated on a dataset of videos containing a variety of sounds (such as ambient sounds and sounds from people or animals).
Proceedings ArticleDOI
Rethinking Self-Attention: Towards Interpretability in Neural Parsing.
TL;DR: The Label Attention Layer is introduced: a new form of self-attention where attention heads represent labels and the Label Attention heads learn relations between syntactic categories and show pathways to analyze errors.
Multimodal Dialogue Management - State of the art
TL;DR: An overview of a multimodal dialogue system and its components is introduced and four main approaches to dialogue management are described (finite-state and frame-based, information-state based and probabilistic, plan-based and collaborative agent-based approaches).