Multi-Module System for Open Domain Chinese Question Answering over Knowledge Base
This work addresses Chinese question answering for knowledge base users, but it is incremental as it combines existing techniques like information retrieval and semantic parsing.
The authors tackled open domain Chinese question answering over a knowledge base by proposing a multi-module system that extracts topic entities and relation predicates to generate Sparql queries, achieving an F1 score of 70.45% on test data.
For the task of open domain Knowledge Based Question Answering in CCKS2019, we propose a method combining information retrieval and semantic parsing. This multi-module system extracts the topic entity and the most related relation predicate from a question and transforms it into a Sparql query statement. Our method obtained the F1 score of 70.45% on the test data.