Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Ngoc Thang Vu

Ngoc Thang Vu

IMS' Systems for the IWSLT 2021 Low-Resource Speech Translation Task

Jun 30, 2021
Pavel Denisov, Manuel Mager, Ngoc Thang Vu

Figure 1 for IMS' Systems for the IWSLT 2021 Low-Resource Speech Translation Task

Figure 2 for IMS' Systems for the IWSLT 2021 Low-Resource Speech Translation Task

Figure 3 for IMS' Systems for the IWSLT 2021 Low-Resource Speech Translation Task

Figure 4 for IMS' Systems for the IWSLT 2021 Low-Resource Speech Translation Task

* IWSLT 2021

Access Paper or Ask Questions

Few-shot Learning for Slot Tagging with Attentive Relational Network

Mar 03, 2021
Cennet Oguz, Ngoc Thang Vu

Figure 1 for Few-shot Learning for Slot Tagging with Attentive Relational Network

Figure 2 for Few-shot Learning for Slot Tagging with Attentive Relational Network

Figure 3 for Few-shot Learning for Slot Tagging with Attentive Relational Network

Figure 4 for Few-shot Learning for Slot Tagging with Attentive Relational Network

* EACL, 5 pages

Access Paper or Ask Questions

Investigations on Audiovisual Emotion Recognition in Noisy Conditions

Mar 02, 2021
Michael Neumann, Ngoc Thang Vu

Figure 1 for Investigations on Audiovisual Emotion Recognition in Noisy Conditions

Figure 2 for Investigations on Audiovisual Emotion Recognition in Noisy Conditions

Figure 3 for Investigations on Audiovisual Emotion Recognition in Noisy Conditions

Figure 4 for Investigations on Audiovisual Emotion Recognition in Noisy Conditions

* Published at the IEEE workshop on Spoken Language Technology (SLT) 2021

Access Paper or Ask Questions

Meta-Learning for improving rare word recognition in end-to-end ASR

Feb 25, 2021
Florian Lux, Ngoc Thang Vu

Figure 1 for Meta-Learning for improving rare word recognition in end-to-end ASR

Figure 2 for Meta-Learning for improving rare word recognition in end-to-end ASR

Figure 3 for Meta-Learning for improving rare word recognition in end-to-end ASR

Figure 4 for Meta-Learning for improving rare word recognition in end-to-end ASR

* Revised version to be published in the proceedings of ICASSP 2021

Access Paper or Ask Questions

Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning

Dec 04, 2020
Daniel Grießhaber, Johannes Maucher, Ngoc Thang Vu

Figure 1 for Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning

Figure 2 for Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning

Figure 3 for Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning

Figure 4 for Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning

* COLING'2020

Access Paper or Ask Questions

F1 is Not Enough! Models and Evaluation Towards User-Centered Explainable Question Answering

Oct 13, 2020
Hendrik Schuff, Heike Adel, Ngoc Thang Vu

Figure 1 for F1 is Not Enough! Models and Evaluation Towards User-Centered Explainable Question Answering

Figure 2 for F1 is Not Enough! Models and Evaluation Towards User-Centered Explainable Question Answering

Figure 3 for F1 is Not Enough! Models and Evaluation Towards User-Centered Explainable Question Answering

Figure 4 for F1 is Not Enough! Models and Evaluation Towards User-Centered Explainable Question Answering

* EMNLP 2020

Access Paper or Ask Questions

Pretrained Semantic Speech Embeddings for End-to-End Spoken Language Understanding via Cross-Modal Teacher-Student Learning

Jul 03, 2020
Pavel Denisov, Ngoc Thang Vu

Figure 1 for Pretrained Semantic Speech Embeddings for End-to-End Spoken Language Understanding via Cross-Modal Teacher-Student Learning

Figure 2 for Pretrained Semantic Speech Embeddings for End-to-End Spoken Language Understanding via Cross-Modal Teacher-Student Learning

Figure 3 for Pretrained Semantic Speech Embeddings for End-to-End Spoken Language Understanding via Cross-Modal Teacher-Student Learning

Figure 4 for Pretrained Semantic Speech Embeddings for End-to-End Spoken Language Understanding via Cross-Modal Teacher-Student Learning

* Submitted to Interspeech 2020

Access Paper or Ask Questions