Sentence Retrieval for Entity List Extraction with a Seed, Context, and Topic
Sentence Retrieval for Entity List Extraction with a Seed, Context, and Topic
复制标题
DOI：
10.1145/3341981.3344250
复制
发表时间：
2019-09
期刊：
影响因子：
--
通讯作者：
Sheikh Muhammad Sarwar;John Foley;Liu Yang;J. Allan
中科院分区：
文献类型：
--
作者：
Sheikh Muhammad Sarwar;John Foley;Liu Yang;J. Allan
我们提出了一个基于语料库的实体集扩展和实体列表完成任务的变化。用户指定的查询和包含一个种子实体的句子是任务的输入。输出是包含输入所指示的实体类的其他实例的句子列表。我们构建了一个语义查询扩展模型，利用种子实体周围的主题上下文和分数的句子。该模型通过平均检索20个句子找到了46%的目标实体类。在20次召回方面，它比BM 25提高了16%。
We present a variation of the corpus-based entity set expansion and entity list completion task. A user-specified query and a sentence containing one seed entity are the input to the task. The output is a list of sentences that contain other instances of the entity class indicated by the input. We construct a semantic query expansion model that leverages topical context around the seed entity and scores sentences. The proposed model finds 46% of the target entity class by retrieving 20 sentences on average. It achieves 16% improvement over BM25 in terms of recall@20.