Skip to content
conftrace_
2019 EMNLP EMNLP 2019

Question Answering Using Hierarchical Attention on Top of BERT Features

Abstract

AbstractThe model submitted works as follows. When supplied a question and a passage it makes use of the BERT embedding along with the hierarchical attention model which consists of 2 parts, the co-attention and the self-attention, to locate a continuous span of the passage that is the answer to the question.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Reham Osama, Nagwa El-Makky, Marwan Torki

Topics

Deep Learning > Architectures > Transformers Natural Language Processing > Applications > Machine Reading Comprehension Natural Language Processing > Applications > Question Answering Artificial Intelligence > Core AI > Attention Deep Learning > Techniques > Attention Mechanism

Keywords

transformer architecture attention mechanism question answering machine reading comprehension pre-trained language model span extraction hierarchical attention transformer model answer span prediction
Download PDF

More from EMNLP 2019

All EMNLP 2019 papers →
Let Me Know What to Ask: Interrogative-Word-Aware Question Generation
Extractive NarrativeQA with Heuristic Pre-Training
CLER: Cross-task Learning with Expert Representation to Generalize Reading and Understanding
Domain-agnostic Question-Answering with Adversarial Training
Generalizing Question Answering System with Pre-trained Language Model Fine-tuning
D-NET: A Pre-Training and Fine-Tuning Framework for Improving the Generalization of Machine Reading Comprehension