论文标题
有效的一通端到端实体链接问题
Efficient One-Pass End-to-End Entity Linking for Questions
论文作者
论文摘要
我们提出ELQ是一个快速的端到端实体链接问题的模型，该模型使用生物编码器共同执行提及检测和链接。在WebQSP和具有扩展注释的图形上进行了评估，每个问题涵盖了多个实体，ELQ的表现分别以 +12.7％和 +19.6％F1的大幅度优于先前的艺术状态。有了非常快的推理时间（单个CPU上的1.57个示例/s），ELQ对于下游的问答系统可能很有用。在概念验证实验中，我们证明，使用ELQ显着提高了GraphReTriever的下游质量检查性能（ARXIV：1911.03868）。代码和数据可在https://github.com/facebookresearch/blink/tree/master/elq那里
We present ELQ, a fast end-to-end entity linking model for questions, which uses a biencoder to jointly perform mention detection and linking in one pass. Evaluated on WebQSP and GraphQuestions with extended annotations that cover multiple entities per question, ELQ outperforms the previous state of the art by a large margin of +12.7% and +19.6% F1, respectively. With a very fast inference time (1.57 examples/s on a single CPU), ELQ can be useful for downstream question answering systems. In a proof-of-concept experiment, we demonstrate that using ELQ significantly improves the downstream QA performance of GraphRetriever (arXiv:1911.03868). Code and data available at https://github.com/facebookresearch/BLINK/tree/master/elq
