End-to-end Biomedical Question Answering via Bio-AnswerFinder and Discriminative Language Representation Models.
CLEF(2021)
Abstract
Generative Transformers based language representation models such as BERT and its biomedical domain adapted version BioBERT have been shown to be highly effective for biomedical question answering. Here, discriminative, sample-efficient biomedical language representation models based on ELECTRA language representation model architecture were introduced to enhance an end-to-end biomedical question answering system, Bio-AnswerFinder, for the BioASQ challenge. The introduced language representation models outperformed other language models including BioBERT in answer span classification, answer candidate re-ranking and yes/no answer classification tasks. The resulting end-to-end system participated in BioASQ Synergy and both phases of Task 9B with promising results.
MoreTranslated text
Key words
discriminative language representation models,end-to-end,bio-answerfinder
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined