Home /

Research

Showing 853 - 858 / 897

Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation


Authors:  HangLe, JuanPino, ChanghanWang....
Published date-11/02/2020
Tasks:  SpeechRecognition

Abstract: We introduce dual-decoder Transformer, a new model architecture that jointly performs automatic speech recognition (ASR) and multilingual speech translation (ST). Our models are based on the original Transformer architecture (Vaswani …

Biased TextRank: Unsupervised Graph-Based Content Extraction


Authors:  AshkanKazemi, VerónicaPérez-Rosas, RadaMihalcea....
Published date-11/02/2020

Abstract: We introduce Biased TextRank, a graph-based content extraction method inspired by the popular TextRank algorithm that ranks text spans according to their importance for language processing tasks and according to …

Valuing Player Actions in Counter-Strike: Global Offensive


Authors:  PeterXenopoulos, HarishDoraiswamy, ClaudioSilva....
Published date-11/02/2020

Abstract: Esports, despite its expanding interest, lacks fundamental sports analytics resources such as accessible data or proven and reproducible analytical frameworks. Even Counter-Strike: Global Offensive (CSGO), the second most popular esport, …

Toward a Generalization Metric for Deep Generative Models


Authors:  HoangThanh-Tung, TruyenTran....
Published date-11/02/2020

Abstract: Measuring the generalization capacity of Deep Generative Models (DGMs) is difficult because of the curse of dimensionality. Evaluation metrics for DGMs like Inception Score, Frechet Inception Distance, Precision-Recall, and Neural …

Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps


Authors:  XanhHo, Anh-KhoaDuongNguyen, SakuSugawara....
Published date-11/02/2020
Tasks:  QuestionAnswering

Abstract: A multi-hop question answering (QA) dataset aims to test reasoning and inference skills by requiring a model to read multiple paragraphs to answer a given question. However, current datasets do …

Image Inpainting with Learnable Feature Imputation


Authors:  HåkonHukkelås, FrankLindseth, RudolfMester....
Published date-11/02/2020
Tasks:  ImageInpainting, Imputation

Abstract: A regular convolution layer applying a filter in the same way over known and unknown areas causes visual artifacts in the inpainted image. Several studies address this issue with feature …

Filter by

Categories

Tags