Stanford at TAC KBP 2017: Building a Trilingual Relational Knowledge Graph

We describe Stanford’s entries in the TAC KBP 2017 Cold Start Knowledge Base Population and Slot Filling challenges. Our biggest contribution is an entirely new Spanish entity detection and relation extraction system for the cross-lingual relation extraction tracks. This new Spanish system is a simple system that uses CRFbased entity recognition supplemented by gazettes followed by several ruled-based relation extractors, some using syntactic structure. We make further improvements to our systems for other languages, including improved named entity recognition, a new neural relation extractor, and better support for nested mentions and discussion forum documents. We also experimented with data fusion with entity linking systems from entrants in the TAC KBP Entity Discovery and Linking challenge. Under the official 2017 macroaveraged MAP all hops score measure, Stanford’s 2017 English, Chinese, Spanish and cross-lingual submissions achieved overall scores of 0.202, 0.124, 0.123, and 0.073, respectively. Under the macroaveraged LDC-MEAN all hops F1 measure used in previous years, the corresponding scores were 0.254, 0.188, 0.186, and 0.117 respectively.