A Study of BERT for Non-Factoid Question-Answering under Passage Length Constraints

08/19/2019
by   Yosi Mass, et al.
0

We study the use of BERT for non-factoid question-answering, focusing on the passage re-ranking task under varying passage lengths. To this end, we explore the fine-tuning of BERT in different learning-to-rank setups, comprising both point-wise and pair-wise methods, resulting in substantial improvements over the state-of-the-art. We then analyze the effectiveness of BERT for different passage lengths and suggest how to cope with large passages.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/14/2019

Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering

Recently, a simple combination of passage retrieval using off-the-shelf ...
research
02/05/2019

End-to-End Open-Domain Question Answering with BERTserini

We demonstrate an end-to-end question answering system that integrates B...
research
05/22/2020

Comparative Study of Machine Learning Models and BERT on SQuAD

This study aims to provide a comparative analysis of performance of cert...
research
02/24/2022

BERTVision – A Parameter-Efficient Approach for Question Answering

We present a highly parameter efficient approach for Question Answering ...
research
02/25/2020

Exploring BERT Parameter Efficiency on the Stanford Question Answering Dataset v2.0

In this paper we explore the parameter efficiency of BERT arXiv:1810.048...
research
10/06/2020

BERT Knows Punta Cana is not just beautiful, it's gorgeous: Ranking Scalar Adjectives with Contextualised Representations

Adjectives like pretty, beautiful and gorgeous describe positive propert...
research
03/04/2020

A Study on Efficiency, Accuracy and Document Structure for Answer Sentence Selection

An essential task of most Question Answering (QA) systems is to re-rank ...

Please sign up or login with your details

Forgot password? Click here to reset