【24h】

BioAMA: Towards an End to End BioMedical Question Answering System

机译:BioAMA:迈向端对端的生物医学问答系统

获取原文

摘要

In this paper, we present a novel Biomedical Question Answering system, BioAMA: "Biomedical Ask Me Anything" on task 5b of the annual BioASQ challenge (Ba-likas et al., 2015). We focus on a wide variety of question types including factoid, list based, summary and yeso type questions that generate both exact and well-formed 'ideal' answers. For summary-type questions, we combine effective IR-based techniques for retrieval and diversification of relevant snippets for a question to create an end-to-end system which achieves a ROUGE-2 score of 0.72 and a ROUGE-SU4 score of 0.71 on ideal answer questions (7% improvement over the previous best model). Additionally, we propose a novel Natural Language Inference (NLI) based framework to answer the yeso questions. To train the NLI model, we also devise a transfer-learning technique by cross-domain projection of word embeddings. Finally, we present a two-stage approach to address the factoid and list type questions by first generating a candidate set using NER taggers and ranking them using both supervised and unsupervised techniques.
机译:在本文中,我们针对年度BioASQ挑战的任务5b(Ba-likas等,2015)提出了一种新颖的生物医学问答系统BioAMA:“ Biomedical Ask Mething”。我们专注于各种各样的问题类型,包括事实类,基于列表的类型,摘要和是/否类型的问题,这些问题会生成准确且格式正确的“理想”答案。对于摘要型问题,我们结合有效的基于IR的技术来检索和简化相关问题的摘要,以创建一个端到端系统,该系统的ROUGE-2得分为0.72,ROUGE-SU4得分为0.71。理想的答案问题(比以前的最佳模型提高了7%)。此外,我们提出了一个新颖的基于自然语言推理(NLI)的框架来回答是/否问题。为了训练NLI模型,我们还设计了一种通过词嵌入的跨域投影的转移学习技术。最后,我们提出一种分两阶段的方法来解决事实和列表类型的问题,方法是首先使用NER标记生成候选集,然后使用有监督和无监督的技术对它们进行排名。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号