Picture for Hongyu Gong

Hongyu Gong

Direct simultaneous speech to speech translation

Add code
Oct 15, 2021
Figure 1 for Direct simultaneous speech to speech translation
Figure 2 for Direct simultaneous speech to speech translation
Viaarxiv icon

Incremental Speech Synthesis For Speech-To-Speech Translation

Add code
Oct 15, 2021
Figure 1 for Incremental Speech Synthesis For Speech-To-Speech Translation
Figure 2 for Incremental Speech Synthesis For Speech-To-Speech Translation
Figure 3 for Incremental Speech Synthesis For Speech-To-Speech Translation
Figure 4 for Incremental Speech Synthesis For Speech-To-Speech Translation
Viaarxiv icon

FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task

Add code
Aug 14, 2021
Figure 1 for FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task
Figure 2 for FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task
Figure 3 for FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task
Figure 4 for FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task
Viaarxiv icon

Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling

Add code
Jun 21, 2021
Figure 1 for Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling
Figure 2 for Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling
Figure 3 for Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling
Figure 4 for Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling
Viaarxiv icon

LAWDR: Language-Agnostic Weighted Document Representations from Pre-trained Models

Add code
Jun 07, 2021
Figure 1 for LAWDR: Language-Agnostic Weighted Document Representations from Pre-trained Models
Figure 2 for LAWDR: Language-Agnostic Weighted Document Representations from Pre-trained Models
Figure 3 for LAWDR: Language-Agnostic Weighted Document Representations from Pre-trained Models
Figure 4 for LAWDR: Language-Agnostic Weighted Document Representations from Pre-trained Models
Viaarxiv icon

Abusive Language Detection in Heterogeneous Contexts: Dataset Collection and the Role of Supervised Attention

Add code
May 24, 2021
Figure 1 for Abusive Language Detection in Heterogeneous Contexts: Dataset Collection and the Role of Supervised Attention
Figure 2 for Abusive Language Detection in Heterogeneous Contexts: Dataset Collection and the Role of Supervised Attention
Figure 3 for Abusive Language Detection in Heterogeneous Contexts: Dataset Collection and the Role of Supervised Attention
Figure 4 for Abusive Language Detection in Heterogeneous Contexts: Dataset Collection and the Role of Supervised Attention
Viaarxiv icon

From Solving a Problem Boldly to Cutting the Gordian Knot: Idiomatic Text Generation

Add code
May 11, 2021
Figure 1 for From Solving a Problem Boldly to Cutting the Gordian Knot: Idiomatic Text Generation
Figure 2 for From Solving a Problem Boldly to Cutting the Gordian Knot: Idiomatic Text Generation
Figure 3 for From Solving a Problem Boldly to Cutting the Gordian Knot: Idiomatic Text Generation
Figure 4 for From Solving a Problem Boldly to Cutting the Gordian Knot: Idiomatic Text Generation
Viaarxiv icon

Demystify Optimization Challenges in Multilingual Transformers

Add code
Apr 20, 2021
Figure 1 for Demystify Optimization Challenges in Multilingual Transformers
Figure 2 for Demystify Optimization Challenges in Multilingual Transformers
Figure 3 for Demystify Optimization Challenges in Multilingual Transformers
Figure 4 for Demystify Optimization Challenges in Multilingual Transformers
Viaarxiv icon

Adaptive Sparse Transformer for Multilingual Translation

Add code
Apr 15, 2021
Figure 1 for Adaptive Sparse Transformer for Multilingual Translation
Figure 2 for Adaptive Sparse Transformer for Multilingual Translation
Figure 3 for Adaptive Sparse Transformer for Multilingual Translation
Figure 4 for Adaptive Sparse Transformer for Multilingual Translation
Viaarxiv icon

Self-Supervised Euphemism Detection and Identification for Content Moderation

Add code
Mar 31, 2021
Figure 1 for Self-Supervised Euphemism Detection and Identification for Content Moderation
Figure 2 for Self-Supervised Euphemism Detection and Identification for Content Moderation
Figure 3 for Self-Supervised Euphemism Detection and Identification for Content Moderation
Figure 4 for Self-Supervised Euphemism Detection and Identification for Content Moderation
Viaarxiv icon