Knowledge Graph Assisted Automatic Sports News Writing
This addresses the problem of automating sports news creation for media and content producers, but it appears incremental as it builds on existing methods like knowledge graphs and neural networks.
The paper tackles automatic sports news writing by extracting pivotal moments from live broadcasts and refining drafts with a sports knowledge graph containing 5,893 entities, achieving confirmed efficiency through evaluations on 50 test cases.
In this paper, we present a novel method for automatically generating sports news, which employs a unique algorithm that extracts pivotal moments from live text broadcasts and uses them to create an initial draft of the news. This draft is further refined by incorporating key details and background information from a specially designed sports knowledge graph. This graph contains 5,893 entities, which are classified into three distinct conceptual categories, interconnected through four relationship types, and characterized by 27 unique attributes. In addition, we create a multi-stage learning model by combining convolutional neural networks and a transformer encoder. This model expresses entity-task interactions using convolutional neural networks and enriches entity representations in the query set with the transformer encoder. It also includes a processor to compute matching scores for incomplete triples, addressing few-shot knowledge graph completion problem. The efficiency of this approach has been confirmed through both subjective and objective evaluations of 50 selected test cases, demonstrating its capability in revolutionizing the creation of sports news.