multi-head attention

CGIM: A Cycle Guided Interactive Learning Model for Consistency Identification in Task-oriented Dialogue COLING 2022 Compositional Attention: Disentangling Search and Retrieval ICLR 2022 Deeply Tensor Compressed Transformers for End-to-End Object Detection AAAI 2022 Detecting Incongruent News Articles Using Multi-head Attention Dual Summarization AACL 2022 Distinguishing Homophenes Using Multi-Head Visual-Audio Memory for Lip Reading AAAI 2022 Doctor Recommendation in Online Health Forums via Expertise Learning ACL 2022 FourierFormer: Transformer Meets Generalized Fourier Integral Theorem NeurIPS 2022 Gaussian Multi-head Attention for Simultaneous Machine Translation ACL 2022 Hero-Gang Neural Model For Named Entity Recognition NAACL 2022 Improving Transformers with Probabilistic Attention Keys ICML 2022 Improving Transformer with an Admixture of Attention Heads NeurIPS 2022 Improving Visual Speech Enhancement Network by Learning Audio-visual Affinity with Multi-head Attention Interspeech 2022 Informative Language Representation Learning for Massively Multilingual Neural Machine Translation COLING 2022 LITE: Intent-based Task Representation Learning Using Weak Supervision NAACL 2022 Measuring the Mixing of Contextual Information in the Transformer EMNLP 2022 Mixture of Attention Heads: Selecting Attention Heads Per Token EMNLP 2022 Neural Window Fully-Connected CRFs for Monocular Depth Estimation CVPR 2022 Pose Guided Human Image Synthesis with Partially Decoupled GAN ACML 2022 Recurrent multi-head attention fusion network for combining audio and text for speech emotion recognition Interspeech 2022 Squeezeformer: An Efficient Transformer for Automatic Speech Recognition NeurIPS 2022 A Health-friendly Speaker Verification System Supporting Mask Wearing AAAI 2021 A Supervised Multi-Head Self-Attention Network for Nested Named Entity Recognition AAAI 2021 Cascaded Head-colliding Attention ACL 2021 Detect Profane Language in Streaming Services to Protect Young Audiences ACL 2021 EL-Attention: Memory Efficient Lossless Attention for Generation ICML 2021