Learn about an innovative approach to machine reading comprehension through this 21-minute conference presentation from SIGIR 2024. Explore the MTMS (Multi-teacher Multi-stage Knowledge Distillation) framework for reasoning-based machine reading comprehension, presented by researchers Zhao Zhuo, Xie Zhiwen, Zhou Guangyou, and Huang Xiangji. Dive into how multiple teacher models and staged knowledge distillation techniques can enhance reading comprehension systems' reasoning capabilities, as demonstrated in this Association for Computing Machinery (ACM) session focused on Question Answering and Summarisation.
Multi-teacher Multi-stage Knowledge Distillation for Reasoning-Based Machine Reading Comprehension
Association for Computing Machinery (ACM) via YouTube
Overview
Syllabus
SIGIR 2024 W1.4 [fp] MTMS: Multi-teacher Multi-stage Knowledge Distillation
Taught by
Association for Computing Machinery (ACM)
Related Courses
-
Self-Improving Teacher Cultivates Better Student: Distillation Calibration for Multimodal Large Language Models - Lecture 3.3
-
CIQA: A Coding Inspired Question Answering Model - Session W1.4
-
Interpretable Graph Routing Network for Knowledge-based Visual Question Answering
-
M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training for Video-text Retrieval
-
Enhancing Sequential Recommenders with Augmented Knowledge from Aligned LLMs - SIGIR 2024
-
Neural Nets for NLP 2021 - Machine Reading with Neural Nets
