Md Akmal Haidar

4 papers · 2021–2022 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird

Venues

COLING (1) EMNLP (1) Interspeech (1) NAACL (1)

Top co-authors

Abbas Ghaddar (3) Mehdi Rezagholizadeh (3) Pascal Poupart (2) Nithin Anchuri (1) Nicola Ferri (1) Felix Weninger (1) Philippe Langlais (1) Yimeng Wu (1) Marco Gaudesi (1) Puming Zhan (1)

Research topics

Machine Learning (4) Application Areas (4) Deep Learning (3) Artificial Intelligence (2) Learning Types · Deep Learning (2) Natural Language Processing (1) Architectures (1) Core AI (1) Learning Paradigms (1) Learning Types · Machine Learning (1) Optimization & Theory (1) Resources & Methods (1)

Keywords

knowledge distillation (4) intermediate layer (2) online learning (1) attention mechanism (1) data augmentation (1) masked language model (1) automatic speech recognition (1) adversarial training (1) pre-trained language model (1) student model (1) teacher model (1) intermediate layer distillation (1) neural network (1) student teacher (1) chunked attention (1) model compression (1) layer mapping (1) contrastive learning (1)

Papers

CILDA: Contrastive Data Augmentation Using Intermediate Layer Knowledge Distillation COLING 2022 Conformer with dual-mode chunked attention for joint online and offline ASR Interspeech 2022 RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation NAACL 2022 Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation EMNLP 2021