文章基本信息

标题：Evaluation of Single-Span Models on Extractive Multi-Span Question-Answering
本地全文：下载
作者：Marie-Anne Xu ; Rahul Khanna
期刊名称：International Journal of Web & Semantic Technology
印刷版ISSN：0976-2280
电子版ISSN：0975-9026
出版年度：2021
卷号：12
期号：1
页码：19-29
DOI：10.5121/ijwest.2021.12102
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Machine Reading Comprehension (MRC), particularly extractive close-domain question-answering, is a prominent field in Natural Language Processing (NLP). Given a question and a passage or set of passages, a machine must be able to extract the appropriate answer from the passage(s). However, the majority of these existing questions have only one answer, and more substantial testing on questions with multiple answers, or multi-span questions, has not yet been applied. Thus, we introduce a newly compiled dataset consisting of questions with multiple answers that originate from previously existing datasets. In addition, we run BERT-based models pre-trained for question-answering on our constructed dataset to evaluate their reading comprehension abilities. Runtime of base models on the entire dataset is approximately one day while the runtime for all models on a third of the dataset is a little over two days. Among the three of BERT-based models we ran, RoBERTa exhibits the highest consistent performance, regardless of size. We find that all our models perform similarly on this new, multi-span dataset compared to the single-span source datasets. While the models tested on the source datasets were slightly fine-tuned in order to return multiple answers, performance is similar enough to judge that task formulation does not drastically affect question-answering abilities. Our evaluations indicate that these models are indeed capable of adjusting to answer questions that require multiple answers. We hope that our findings will assist future development in question-answering and improve existing question-answering products and methods.
其他摘要：Machine Reading Comprehension (MRC), particularly extractive close-domain question-answering, is a prominent field in Natural Language Processing (NLP). Given a question and a passage or set of passages, a machine must be able to extract the appropriate answer from the passage(s). However, the majority of these existing questions have only one answer, and more substantial testing on questions with multiple answers, or multi-span questions, has not yet been applied. Thus, we introduce a newly compiled dataset consisting of questions with multiple answers that originate from previously existing datasets. In addition, we run BERT-based models pre-trained for question-answering on our constructed dataset to evaluate their reading comprehension abilities. Runtime of base models on the entire dataset is approximately one day while the runtime for all models on a third of the dataset is a little over two days. Among the three of BERT-based models we ran, RoBERTa exhibits the highest consistent performance, regardless of size. We find that all our models perform similarly on this new, multi-span dataset compared to the single-span source datasets. While the models tested on the source datasets were slightly fine-tuned in order to return multiple answers, performance is similar enough to judge that task formulation does not drastically affect question-answering abilities. Our evaluations indicate that these models are indeed capable of adjusting to answer questions that require multiple answers. We hope that our findings will assist future development in question-answering and improve existing question-answering products and methods.
关键词：Natural Language Processing; Question Answering; Machine Reading Comprehension