Search Results for author:
Found 11 papers, 3 papers with code
WebNLG Challenge 2020: Language Agnostic Delexicalisation for Multilingual RDF-to-text generation
This paper presents our submission to the WebNLG Challenge 2020 for the English and Russian RDF-to-text generation tasks.
Hierarchical Recurrent Aggregative Generation for Few-Shot NLG
Large pretrained models enable transfer learning to low-resource domains for language generation tasks.
Multi-Vector Attention Models for Deep Re-ranking
Large-scale document retrieval systems often utilize two styles of neural network models which live at two different ends of the joint computation vs. accuracy spectrum.
Prosody in Cascade and Direct Speech-to-Text Translation: a case study on Korean Wh-Phrases
While there has been a growing interest in developing direct speech translation systems to avoid propagating errors and losing non-verbal content, prior work in direct S2TT has struggled to conclusively establish the advantages of integrating the acoustic signal directly into the translation process.
A Field Test of Bandit Algorithms for Recommendations: Understanding the Validity of Assumptions on Human Preferences in Multi-armed Bandits
While answering these questions, we provide a flexible experimental framework for understanding human preference dynamics and testing MABs algorithms with human users.
Generalising Multilingual Concept-to-Text NLG with Language Agnostic Delexicalisation
In this paper, we explore the application of multilingual models in concept-to-text and propose Language Agnostic Delexicalisation, a novel delexicalisation method that uses multilingual pretrained embeddings, and employs a character-level post-editing model to inflect words in their correct form during relexicalisation.
Informed Sampling for Diversity in Concept-to-Text NLG
In this work, we propose to ameliorate this cost by using an Imitation Learning approach to explore the level of diversity that a language generation model can reliably produce.
Accelerating Deep Learning by Focusing on the Biggest Losers
This paper introduces Selective-Backprop, a technique that accelerates the training of deep neural networks (DNNs) by prioritizing examples with high loss at each iteration.
Scaling Video Analytics on Constrained Edge Nodes
As video camera deployments continue to grow, the need to process large volumes of real-time data strains wide area network infrastructure.
EDF: Ensemble, Distill, and Fuse for Easy Video Labeling
We present a way to rapidly bootstrap object detection on unseen videos using minimal human annotations.
Clipper: A Low-Latency Online Prediction Serving System
In this paper, we introduce Clipper, a general-purpose low-latency prediction serving system.
