1.5k citations · 3.3k across the 54 of their papers we have counts for
17 papers · 1 filter
Visually-augmented pretrained language models for NLP tasks without images
Hangyu Guo, Kun Zhou, Wayne Xin Zhao +2
Although pre-trained language models~(PLMs) have shown impressive performance by text-only self-supervised training, they are found lack of visual semantics or commonsense. Existin…
MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders are Better Dense Retrievers
Kun Zhou, Xiao Liu, Yeyun Gong +4
Pre-trained Transformers (\eg BERT) have been commonly used in existing dense retrieval methods for parameter initialization, and recent studies are exploring more effective pre-tr…
UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph
Jinhao Jiang, Kun Zhou, Wayne Xin Zhao +1
Multi-hop Question Answering over Knowledge Graph~(KGQA) aims to find the answer entities that are multiple hops away from the topic entities mentioned in a natural language questi…
SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval
Kun Zhou, Yeyun Gong, Xiao Liu +8
Sampling proper negatives from a large document pool is vital to effectively train a dense retrieval model. However, existing negative sampling strategies suffer from the uninforma…
Mixed-EVC: Mixed Emotion Synthesis and Control in Voice Conversion
Kun Zhou, Berrak Sisman, Carlos Busso +2
Emotional voice conversion (EVC) traditionally targets the transformation of spoken utterances from one emotional state to another, with previous research mainly focusing on discre…
Speech Synthesis with Mixed Emotions
Kun Zhou, Berrak Sisman, Rajib Rana +2
Emotional speech synthesis aims to synthesize human voices with various emotional effects. The current studies are mostly focused on imitating an averaged style belonging to a spec…