Correct after Answer: Enhancing Multi-Span Question Answering with Post-Processing Method

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Jiayi, Zhang, Chenyang, Tong, Haibo, Zhang, Dongyu, Hong, Qingqing, Hou, Bingxuan, Wang, Junli
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914983666778112
author Lin, Jiayi
Zhang, Chenyang
Tong, Haibo
Zhang, Dongyu
Hong, Qingqing
Hou, Bingxuan
Wang, Junli
author_facet Lin, Jiayi
Zhang, Chenyang
Tong, Haibo
Zhang, Dongyu
Hong, Qingqing
Hou, Bingxuan
Wang, Junli
contents Multi-Span Question Answering (MSQA) requires models to extract one or multiple answer spans from a given context to answer a question. Prior work mainly focuses on designing specific methods or applying heuristic strategies to encourage models to predict more correct predictions. However, these models are trained on gold answers and fail to consider the incorrect predictions. Through a statistical analysis, we observe that models with stronger abilities do not predict less incorrect predictions compared with other models. In this work, we propose Answering-Classifying-Correcting (ACC) framework, which employs a post-processing strategy to handle incorrect predictions. Specifically, the ACC framework first introduces a classifier to classify the predictions into three types and exclude "wrong predictions", then introduces a corrector to modify "partially correct predictions". Experiments on several MSQA datasets show that ACC framework significantly improves the Exact Match (EM) scores, and further analysis demostrates that ACC framework efficiently reduces the number of incorrect predictions, improving the quality of predictions.
format Preprint
id arxiv_https___arxiv_org_abs_2410_16788
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Correct after Answer: Enhancing Multi-Span Question Answering with Post-Processing Method
Lin, Jiayi
Zhang, Chenyang
Tong, Haibo
Zhang, Dongyu
Hong, Qingqing
Hou, Bingxuan
Wang, Junli
Computation and Language
Artificial Intelligence
Multi-Span Question Answering (MSQA) requires models to extract one or multiple answer spans from a given context to answer a question. Prior work mainly focuses on designing specific methods or applying heuristic strategies to encourage models to predict more correct predictions. However, these models are trained on gold answers and fail to consider the incorrect predictions. Through a statistical analysis, we observe that models with stronger abilities do not predict less incorrect predictions compared with other models. In this work, we propose Answering-Classifying-Correcting (ACC) framework, which employs a post-processing strategy to handle incorrect predictions. Specifically, the ACC framework first introduces a classifier to classify the predictions into three types and exclude "wrong predictions", then introduces a corrector to modify "partially correct predictions". Experiments on several MSQA datasets show that ACC framework significantly improves the Exact Match (EM) scores, and further analysis demostrates that ACC framework efficiently reduces the number of incorrect predictions, improving the quality of predictions.
title Correct after Answer: Enhancing Multi-Span Question Answering with Post-Processing Method
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.16788