Au sujet de ce document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Georg Wiese
- sl:arxiv_num : 1706.03610
- sl:arxiv_published : 2017-06-12T13:08:21Z
- sl:arxiv_summary : Factoid question answering (QA) has recently benefited from the development
of deep learning (DL) systems. Neural network models outperform traditional
approaches in domains where large datasets exist, such as SQuAD (ca. 100,000
questions) for Wikipedia articles. However, these systems have not yet been
applied to QA in more specific domains, such as biomedicine, because datasets
are generally too small to train a DL system from scratch. For example, the
BioASQ dataset for biomedical QA comprises less then 900 factoid (single
answer) and list (multiple answers) QA instances. In this work, we adapt a
neural QA system trained on a large open-domain dataset (SQuAD, source) to a
biomedical dataset (BioASQ, target) by employing various transfer learning
techniques. Our network architecture is based on a state-of-the-art QA system,
extended with biomedical word embeddings and a novel mechanism to answer list
questions. In contrast to existing biomedical QA systems, our system does not
rely on domain-specific ontologies, parsers or entity taggers, which are
expensive to create. Despite this fact, our systems achieve state-of-the-art
results on factoid questions and competitive results on list questions.@en
- sl:arxiv_title : Neural Domain Adaptation for Biomedical Question Answering@en
- sl:arxiv_updated : 2017-06-15T15:16:18Z
- sl:bookmarkOf : https://arxiv.org/abs/1706.03610
- sl:creationDate : 2021-11-19
- sl:creationTime : 2021-11-19T00:09:38Z
Documents with similar tags (experimental)
Préférences...