LegoNN: Building Modular Encoder-Decoder Models

LegoNN: Building Modular Encoder-Decoder Models

7 June 2022

Siddharth Dalmia

Sergey Edunov

Shinji Watanabe

Luke Zettlemoyer

Abdel-rahman Mohamed

Papers citing "LegoNN: Building Modular Encoder-Decoder Models"

8 / 8 papers shown

Title
Coupling Speech Encoders with Downstream Text Models Ciprian Chelba J. Schalkwyk AuLLM 22 0 0 24 Jul 2024
LLM Augmented LLMs: Expanding Capabilities through Composition Rachit Bansal Bidisha Samanta Siddharth Dalmia Nitish Gupta Shikhar Vashishth Sriram Ganapathy Abhishek Bapna Prateek Jain Partha P. Talukdar CLL 21 34 0 04 Jan 2024
Leveraging Multilingual Self-Supervised Pretrained Models for Sequence-to-Sequence End-to-End Spoken Language Understanding Pavel Denisov Ngoc Thang Vu 29 1 0 09 Oct 2023
Lego-Features: Exporting modular encoder features for streaming and deliberation ASR Rami Botros Rohit Prabhavalkar J. Schalkwyk Ciprian Chelba Tara N. Sainath Franccoise Beaufays AuLLM 13 2 0 31 Mar 2023
Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translation Fei Yuan Yinquan Lu Wenhao Zhu Lingpeng Kong Lei Li Yu Qiao Jingjing Xu MoE 25 22 0 20 Dec 2022
Accelerating RNN-T Training and Inference Using CTC guidance Yongqiang Wang Zhehuai Chen Cheng-yong Zheng Yu Zhang Wei Han Parisa Haghani 32 23 0 29 Oct 2022
CTC Alignments Improve Autoregressive Translation Brian Yan Siddharth Dalmia Yosuke Higuchi Graham Neubig Florian Metze A. Black Shinji Watanabe 41 33 0 11 Oct 2022
Effective Approaches to Attention-based Neural Machine Translation Thang Luong Hieu H. Pham Christopher D. Manning 214 7,687 0 17 Aug 2015