Home /

Research

Showing 811 - 816 / 897

Detecting Word Sense Disambiguation Biases in Machine Translation for Model-Agnostic Adversarial Attacks


Authors:  DenisEmelin, IvanTitov, RicoSennrich....
Published date-11/03/2020
Tasks:  AdversarialAttack, MachineTranslation, WordSenseDisambiguation

Abstract: Word sense disambiguation is a well-known source of translation errors in NMT. We posit that some of the incorrect disambiguation choices are due to models' over-reliance on dataset artifacts found …

Learning 3D Dynamic Scene Representations for Robot Manipulation


Authors:  ZhenjiaXu, ZhanpengHe, JiajunWu....
Published date-11/03/2020

Abstract: 3D scene representation for robot manipulation should capture three key object properties: permanency -- objects that become occluded over time continue to exist; amodal completeness -- objects have 3D occupancy, …

Control with adaptive Q-learning


Authors:  JoãoPedroAraújo, MárioA.T.Figueiredo, MiguelAyalaBotto....
Published date-11/03/2020
Tasks:  OpenAIGym, Q-Learning

Abstract: This paper evaluates adaptive Q-learning (AQL) and single-partition adaptive Q-learning (SPAQL), two algorithms for efficient model-free episodic reinforcement learning (RL), in two classical control problems (Pendulum and Cartpole). AQL adaptively …

Cross-Media Keyphrase Prediction: A Unified Framework with Multi-Modality Multi-Head Attention and Image Wordings


Authors:  YueWang, JingLi, MichaelR.Lyu....
Published date-11/03/2020

Abstract: Social media produces large amounts of contents every day. To help users quickly capture what they need, keyphrase prediction is receiving a growing attention. Nevertheless, most prior efforts focus on …

CharBERT: Character-aware Pre-trained Language Model


Authors:  WentaoMa, YimingCui, ChengleiSi....
Published date-11/03/2020
Tasks:  LanguageModelling, QuestionAnswering, RepresentationLearning, TextClassification

Abstract: Most pre-trained language models (PLMs) construct word representations at subword level with Byte-Pair Encoding (BPE) or its variations, by which OOV (out-of-vocab) words are almost avoidable. However, those methods split …

Amortized Variational Deep Q Network


Authors:  HaotianZhang, YuhaoWang, JianyongSun....
Published date-11/03/2020
Tasks:  EfficientExploration, OpenAIGym, VariationalInference

Abstract: Efficient exploration is one of the most important issues in deep reinforcement learning. To address this issue, recent methods consider the value function parameters as random variables, and resort variational …

Filter by

Categories

Tags