Alert button

"Text": models, code, and papers
Alert button

Domain Adaptation of Transformer-Based Models using Unlabeled Data for Relevance and Polarity Classification of German Customer Feedback

Dec 12, 2022
Ahmad Idrissi-Yaghir, Henning Schäfer, Nadja Bauer, Christoph M. Friedrich

Figure 1 for Domain Adaptation of Transformer-Based Models using Unlabeled Data for Relevance and Polarity Classification of German Customer Feedback
Figure 2 for Domain Adaptation of Transformer-Based Models using Unlabeled Data for Relevance and Polarity Classification of German Customer Feedback
Figure 3 for Domain Adaptation of Transformer-Based Models using Unlabeled Data for Relevance and Polarity Classification of German Customer Feedback
Figure 4 for Domain Adaptation of Transformer-Based Models using Unlabeled Data for Relevance and Polarity Classification of German Customer Feedback
Viaarxiv icon

Fast and Accurate FSA System Using ELBERT: An Efficient and Lightweight BERT

Nov 16, 2022
Siyuan Lu, Chenchen Zhou, Keli Xie, Shiyi Liu, Jun Lin, Zhongfeng Wang

Figure 1 for Fast and Accurate FSA System Using ELBERT: An Efficient and Lightweight BERT
Figure 2 for Fast and Accurate FSA System Using ELBERT: An Efficient and Lightweight BERT
Figure 3 for Fast and Accurate FSA System Using ELBERT: An Efficient and Lightweight BERT
Figure 4 for Fast and Accurate FSA System Using ELBERT: An Efficient and Lightweight BERT
Viaarxiv icon

Sinhala Sentence Embedding: A Two-Tiered Structure for Low-Resource Languages

Oct 26, 2022
Gihan Weeraprameshwara, Vihanga Jayawickrama, Nisansa de Silva, Yudhanjaya Wijeratne

Figure 1 for Sinhala Sentence Embedding: A Two-Tiered Structure for Low-Resource Languages
Figure 2 for Sinhala Sentence Embedding: A Two-Tiered Structure for Low-Resource Languages
Figure 3 for Sinhala Sentence Embedding: A Two-Tiered Structure for Low-Resource Languages
Figure 4 for Sinhala Sentence Embedding: A Two-Tiered Structure for Low-Resource Languages
Viaarxiv icon

iQuery: Instruments as Queries for Audio-Visual Sound Separation

Dec 08, 2022
Jiaben Chen, Renrui Zhang, Dongze Lian, Jiaqi Yang, Ziyao Zeng, Jianbo Shi

Figure 1 for iQuery: Instruments as Queries for Audio-Visual Sound Separation
Figure 2 for iQuery: Instruments as Queries for Audio-Visual Sound Separation
Figure 3 for iQuery: Instruments as Queries for Audio-Visual Sound Separation
Figure 4 for iQuery: Instruments as Queries for Audio-Visual Sound Separation
Viaarxiv icon

Non-Parallel Text Style Transfer with Self-Parallel Supervision

Apr 18, 2022
Ruibo Liu, Chongyang Gao, Chenyan Jia, Guangxuan Xu, Soroush Vosoughi

Figure 1 for Non-Parallel Text Style Transfer with Self-Parallel Supervision
Figure 2 for Non-Parallel Text Style Transfer with Self-Parallel Supervision
Figure 3 for Non-Parallel Text Style Transfer with Self-Parallel Supervision
Figure 4 for Non-Parallel Text Style Transfer with Self-Parallel Supervision
Viaarxiv icon

JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech

Mar 31, 2022
Dan Lim, Sunghee Jung, Eesung Kim

Figure 1 for JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech
Figure 2 for JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech
Figure 3 for JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech
Viaarxiv icon

Language Matters: A Weakly Supervised Pre-training Approach for Scene Text Detection and Spotting

Mar 08, 2022
Chuhui Xue, Yu Hao, Shijian Lu, Philip Torr, Song Bai

Figure 1 for Language Matters: A Weakly Supervised Pre-training Approach for Scene Text Detection and Spotting
Figure 2 for Language Matters: A Weakly Supervised Pre-training Approach for Scene Text Detection and Spotting
Figure 3 for Language Matters: A Weakly Supervised Pre-training Approach for Scene Text Detection and Spotting
Figure 4 for Language Matters: A Weakly Supervised Pre-training Approach for Scene Text Detection and Spotting
Viaarxiv icon

AgAsk: An Agent to Help Answer Farmer's Questions From Scientific Documents

Dec 21, 2022
Bevan Koopman, Ahmed Mourad, Hang Li, Anton van der Vegt, Shengyao Zhuang, Simon Gibson, Yash Dang, David Lawrence, Guido Zuccon

Figure 1 for AgAsk: An Agent to Help Answer Farmer's Questions From Scientific Documents
Figure 2 for AgAsk: An Agent to Help Answer Farmer's Questions From Scientific Documents
Figure 3 for AgAsk: An Agent to Help Answer Farmer's Questions From Scientific Documents
Figure 4 for AgAsk: An Agent to Help Answer Farmer's Questions From Scientific Documents
Viaarxiv icon

JASMINE: Arabic GPT Models for Few-Shot Learning

Dec 21, 2022
El Moatez Billah Nagoudi, Muhammad Abdul-Mageed, AbdelRahim Elmadany, Alcides Alcoba Inciarte, Md Tawkat Islam Khondaker

Figure 1 for JASMINE: Arabic GPT Models for Few-Shot Learning
Figure 2 for JASMINE: Arabic GPT Models for Few-Shot Learning
Figure 3 for JASMINE: Arabic GPT Models for Few-Shot Learning
Figure 4 for JASMINE: Arabic GPT Models for Few-Shot Learning
Viaarxiv icon

EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance Segmentation

Dec 15, 2022
Yunhao Ge, Jiashu Xu, Brian Nlong Zhao, Laurent Itti, Vibhav Vineet

Figure 1 for EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance Segmentation
Figure 2 for EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance Segmentation
Figure 3 for EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance Segmentation
Figure 4 for EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance Segmentation
Viaarxiv icon