IR实验室参加CHIP 2018健康咨询问句匹配大赛获得第一名
新闻来源:IR实验室       发布时间:2018/12/4 23:54:27

  12月1-2日于深圳召开的第四届中国健康信息处理大会(CHIP2018)的技术评测中,实验室硕士生岳天驰、李英东、汶东震等组队获得《平安医疗科技智能患者健康咨询问句匹配大赛》第一名,据统计本次比赛共计一百零八支队伍报名参赛,经官方核查后确定有效提交共有六十支队伍。

1.jpg

  问句匹配是自然语言处理的最基本任务之一,是自动问答、聊天机器人、信息检索、机器翻译等各种自然语言处理任务基础。问句匹配的主要目的是判断两个问句之间的语义是否等价。因此,其核心是语句的意图匹配。由于来源于真实问答语料库,该任务更加接近于智能医疗助手等自然语言处理任务的实际需求。

2.jpg

  本次评测任务的主要目标是针对中文的真实患者健康咨询语料,进行问句意图匹配。给定两个语句,要求判定两者意图是否相同或者相近。所有语料来自互联网上患者真实的问题,并经过了筛选和人工的意图匹配标注。

3.jpg

  本次会议我实验室博士生赵迪的论文:Relation Path  Feature Embedding based Convolutional Neural Network Method for Drug Discovery,被会议录用为poster并在会场做了交流,反响较好。

4.jpg

  论文摘要如下:

  Abstract:Drug development is an expensive and time-consuming process. Literature-based discovery has played a critical role in drug development and may be a supplementary method to help scientists speed up the discovery of drugs. Here, we propose a relation path features embedding based convolutional neural network model with attention mechanism for drug discovery from literature, which we denote as PACNN. First, we use predications from biomedical abstracts to construct a biomedical knowledge graph, and then apply a path ranking algorithm to extract drug-disease relation path features on the biomedical knowledge graph. After that, we use these drug-disease relation features to train a convolutional neural network model which combined with the attention mechanism. Finally, we employ the trained models to mine drugs for treating diseases. The experiment shows that the proposed model achieved promising results, comparing to several random walk algorithms.